Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover idempotency and non-destructiveness. The description adds 'Returns: Confirmation of reaction added' but no further behavioral context beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (3 lines), front-loaded with the purpose, and efficiently structured with Args and Returns sections. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter tool with no output schema, the description fully covers what the tool does, its inputs, and its output. It is complete for correct agent usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema fully describes parameters. The description adds an emoji example and return type, but does not significantly enhance parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Add an emoji reaction to a message' with a specific verb and resource. It distinguishes from siblings like discord_remove_reaction and discord_send_message.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool over alternatives. However, the purpose is clear from the name and context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate non-readOnly (write), non-destructive, and idempotent. The description adds no behavioral context beyond 'Add', such as permission requirements or side effects. It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences, three bullet points, and a return note. Every sentence adds value with no redundancy, and the purpose is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple write operation with clear annotations and full schema coverage, the description is nearly complete. It lacks mention of error conditions or explicit prerequisites but covers the core behavior and parameters adequately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description simply restates the parameter names without adding meaning beyond the schema's existing descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Add a role to a Discord member' uses a specific verb ('Add') and resource ('role to a Discord member'), clearly distinguishing it from sibling tools like 'discord_remove_role' (removes) and 'discord_create_role' (creates).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance is provided. The description implies usage context but does not mention prerequisites (e.g., role must exist, member in guild) or alternative tools like 'discord_create_role'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide destructiveHint=true and readOnlyHint=false. The description adds that the reason is visible in audit logs and delete_message_days controls message deletion. However, it fails to disclose irreversibility implications, permission requirements (e.g., 'Ban Members' permission), or error handling for already-banned users.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a clear summary, argument list, and return value. No unnecessary repetition; well-structured for quick parsing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 4 parameters and no output schema, the description covers the basic action and parameters. It lacks details on error scenarios and permissions but is sufficient for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented. The description adds value by stating the default for delete_message_days as 0, which is not in the schema. Otherwise, it largely restates schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool bans a member from a Discord server. However, it does not differentiate from sibling tools like kick or timeout, missing an opportunity to distinguish scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as discord_kick_member or discord_unban_member. No context on selection criteria or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description aligns with annotations (non-read-only, non-destructive). It notes return details but lacks permissions, side effects, or error conditions. Annotations supply behavioral safety hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with headings, Arg list, and Returns. Mostly concise, though the Arg list partially duplicates schema. First sentence is clear and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all inputs, but lacks output schema for return value structure and missing prerequisites like required permissions. Reasonably complete given complexity, but could be improved.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains parameters. The description rephrases minimal context but adds little beyond defaults or optionality already in schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The verb 'Create' clearly states the action, and 'automod rule' specifies the resource. It distinguishes from sibling tools like discord_edit_automod_rule, discord_delete_automod_rule, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use vs alternatives (e.g., editing or listing rules). Usage is implied by the tool name and description, but no direct comparison.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate a write operation (readOnlyHint false) and no destructive or idempotent behavior. The description adds no additional behavioral context beyond what the annotations provide, such as permission requirements, rate limits, or error conditions (e.g., duplicate names).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with Args and Returns sections, making it easy to scan. However, it is verbose, listing all 12 parameters in detail when a shorter summary could suffice. Still, the structure earns a high score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of 12 parameters (2 required) and no output schema, the description thoroughly documents each parameter's purpose, type, constraints, and defaults. It covers all necessary details for an agent to correctly invoke the tool, leaving no obvious gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, meaning all parameters have schema descriptions. The description largely repeats this information with a structured Args list, adding marginal value like inline defaults and notes (e.g., 'not for categories' for parent_id). This provides some extra clarity but doesn't significantly surpass the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Create a new channel or category in a Discord server', clearly identifying the verb (create) and resource (channel/category). This distinguishes it from sibling tools like discord_edit_channel and discord_delete_channel.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no direct guidance on when to use this tool vs alternatives (e.g., when to create a category vs text channel, or when to use discord_edit_channel). The context is implied by the tool name and parameter types, but explicit usage instructions are missing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate it is not read-only, not idempotent, and not destructive. The description adds return info but does not discuss permissions, rate limits, or edge cases. It adds some value beyond annotations by specifying image constraints (PNG, JPG, GIF, <256KB).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with separate Args and Returns sections. It is front-loaded with purpose and parameter details, but the extra `roles` param adds unnecessary length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with 3 parameters, the description covers purpose, parameters, and returns. However, it lacks prerequisites (e.g., 'Manage Emoji' permission), error handling info, and uniqueness constraints for emoji names. Given no output schema, it could provide more context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but the description adds an optional `roles` parameter not present in the schema, causing inconsistency. It does provide additional constraints for `image_url` (file type, size) not in schema, which is helpful. Overall, it adds some value but also confusion.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a custom emoji in a server,' using a specific verb and resource. It distinguishes from sibling tools like `discord_add_reaction` (adds existing emoji) and `discord_delete_emoji` (deletes emoji).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

While no explicit alternatives are given, the purpose is clear among siblings that have different actions (add, delete, list). The description provides parameter context, but lacks explicit guidance on when to use vs. other emoji-related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate it's not read-only (readOnlyHint=false) and may have open-world side effects. The description discloses it creates an event but does not elaborate on permissions, rate limits, or failure behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long due to parameter listing, but it is structured with Args and Returns sections. It front-loads the main action. However, it repeats schema information which could be more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema given, the description mentions 'Created event details' but not fields. There is inconsistency: description lists 'location' as a separate parameter, but schema nests it inside 'entity_metadata'. Does not explain that scheduled_end_time is required for external events (schema mentions it).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description adds limited new meaning. It lists parameters with types and optionality, but essentially repeats schema info. Minor added value in clarifying entity_type enum and location field.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a scheduled event in a server', specifying the action and resource. It distinguishes from sibling tools like discord_list_events (read) and discord_delete_event (delete).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. No mention of prerequisites like required permissions or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description explains all parameters and return value, including behavior of temporary and unique. Annotations indicate no destructive or idempotent effects, which matches. Could mention rate limits or permission checks, but current detail is good.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and well-structured: one-line summary, then Args list, then Returns. No fluff, every sentence adds information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all parameters and return value. Lacks error cases, rate limits, or permission requirements. Given no output schema, the return description is adequate. Slightly above average completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% description coverage, so baseline is 3. Description adds value by clarifying parameter behavior (e.g., 'Kick members when they disconnect' for temporary, 'reuse existing' for unique). Marginally above baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'Create' and the resource 'invite link for a channel'. It is specific and distinguishes this tool from siblings like discord_delete_invite and discord_list_invites.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. Does not indicate prerequisites like permissions or when not to use it. Missing explicit when-to-use/not-use or sibling differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate write operation (readOnlyHint=false) and non-destructive, which aligns with description. The description adds default values for mentionable and hoist (false) and states it returns role details, providing behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: a single line of purpose followed by a structured argument list. Every sentence adds value; no wasted words. Front-loaded with the action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters and no output schema, the description covers all parameters with defaults and return info. It lacks permission or error context, but is sufficient for a creation tool with openWorldHint=true.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). The description adds value by including defaults for mentionable and hoist, an example for color, and a clear mapping of args. It improves over the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a new role in a Discord server', using a specific verb and resource. It distinguishes itself from sibling tools like discord_edit_role and discord_delete_role by focusing on creation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like discord_edit_role. The purpose is implied from the name, but no when-not-to-use or alternative references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate a non-readOnly, non-idempotent write operation. The description adds no further behavioral context such as required permissions, rate limits, or side effects beyond stating it creates a webhook and returns details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured with an args list and return statement. It efficiently conveys necessary information without verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the basics: parameters and return value. However, it lacks context about permissions, webhook limits, or typical use cases, which would be helpful given the presence of many sibling tools and no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for all parameters. The description lists parameters but adds no additional meaning beyond what the schema provides, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create'), resource ('webhook'), and scope ('in a channel'). It effectively distinguishes from sibling tools like discord_edit_webhook and discord_delete_webhook.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., discord_create_channel for other creations), prerequisites, or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already indicate destructiveHint: true. The description adds that the tool returns a 'Confirmation of deletion', but does not elaborate on irreversible consequences or permission requirements. It adds only minimal behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: one purpose sentence, an args list, and a returns line. It is front-loaded with the purpose and contains no extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple destructive action, the description covers the core operation and return value. However, it lacks context about required permissions, error handling, or how the confirmation is structured. Still, it is largely sufficient given the annotations that already signal destructive behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers both parameters with descriptions, patterns, and length constraints (100% coverage). The description merely repeats the same information without adding new semantics or examples, so it meets the baseline but does not improve clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Delete an auto moderation rule from a server', specifying the action (delete) and the resource (auto moderation rule). It effectively distinguishes this tool from sibling tools like create, edit, get, and list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites (e.g., required permissions), and no conditions for use. It only states the action and arguments.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds the warning 'This action is permanent!' and mentions return confirmation, which reinforces but does not significantly extend the behavioral information provided by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two clear sections: a brief statement of action and permanence, followed by structured Args/Returns. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple destructive tool with one parameter and no output schema, the description fully covers what the tool does, its key behavioral trait (permanence), and the required input. No missing information for the agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers the single parameter with 100% coverage including pattern and description. The description merely restates the parameter name and type without adding new semantic meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Delete' and resource 'channel', matching the tool name. It distinguishes from sibling tools like discord_edit_channel and discord_create_channel by explicitly stating deletion.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as editing, archiving, or other channel operations. The only context is a warning about permanence, but no usage context or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructiveHint=true and idempotentHint=true. Description adds 'confirmation of deletion' but lacks details like permission requirements or error handling, offering minimal extra value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is short and to the point, with an args/returns structure. However, the args section largely duplicates schema info, slightly reducing conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With full schema and annotations, the description is functionally sufficient for a simple tool, but lacks additional context like required permissions or effects on non-existent emojis.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed param descriptions. The description just lists param names without adding new meaning, meeting the baseline for full schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool deletes a custom emoji from a server, using a specific verb and resource. It effectively distinguishes from sibling tools like discord_create_emoji and discord_list_emojis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use when deletion is needed but provides no explicit guidance on when to use vs alternatives, nor any exclusions or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true. The description says 'Delete' and 'Returns confirmation', which aligns with annotations but adds no additional behavioral context beyond what is already indicated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, with no wasted words. It front-loads the purpose and lists arguments clearly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 2 required parameters, no output schema, and full annotations, the description covers the essential information: what it does, required args, and return type.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters. The description's Args list merely repeats the schema's descriptions without adding new meaning or format details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The title 'Delete Scheduled Event' and description 'Delete a scheduled event from a server.' clearly state the action and resource. It distinguishes from sibling tools like discord_create_event and discord_list_events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides an Args list and Return info, but no explicit guidance on when to use vs alternatives or when not to use. The context is clear but lacks exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructive (destructiveHint=true) and idempotent (idempotentHint=true) behavior. The description adds that a confirmation is returned but offers no additional behavioral context (e.g., that deleted invites become invalid immediately).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with the purpose. The 'Args' and 'Returns' sections are clear but a bit verbose for a single parameter; could be tighter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple, one-parameter, destructive tool with good annotation coverage, the description is adequate but lacks specifics about the return format or what 'Confirmation of deletion' entails.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema description coverage, the description merely restates the invite_code parameter and its purpose, adding no extra meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete') and the resource ('invite by its code'), distinguishing it from sibling tools like discord_create_invite or discord_list_invites.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for deleting invites but provides no context on when to use this tool versus alternatives like revoking invite permissions or pruning members.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (destructiveHint=true) already indicate the tool modifies state. The description adds a return type ('Confirmation of deletion') but omits details like rate limits, idempotency, or behavior on missing messages. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (two sentences plus bulleted args and return). Every line serves a purpose: purpose, arguments, and return value. No fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple deletion tool with comprehensive schema and annotations, the description covers the core function, parameters, and return. Missing edge case handling (e.g., permissions) is acceptable given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions (snowflake pattern, length constraints). The description restates these concisely ('Discord channel ID', 'Message ID to delete') but adds no new semantic information beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Delete a message from a Discord channel' using a specific verb and resource. Among sibling tools with 'delete_' prefix, it uniquely targets messages, distinguishing itself from delete_channel, delete_role, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites (e.g., permissions needed), and no exclusions. The agent must infer usage solely from the name and destructiveHint annotation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds 'This action is permanent!' which reinforces the destructive nature but does not elaborate on specific behavioral details like permission requirements or downstream effects on members.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with three clear sections (action, args, returns). No unnecessary words, but the args section could be integrated more succinctly with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple deletion tool with full schema coverage and annotations, the description covers the core action, permanence, parameters, and return type. It lacks potential error conditions or prerequisite handling, but is largely complete for typical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions (e.g., snowflake patterns). The description repeats parameter names and types but adds no new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Delete a role from a Discord server' with a specific verb and resource, and emphasizes permanence. It distinguishes itself from sibling tools like discord_create_role and discord_edit_role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool, preconditions (e.g., permissions), or when not to use it. It lacks explicit context for an agent to decide between this and other role-related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true. The description adds return info ('Confirmation of deletion'), but no additional behavioral context beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: one sentence for purpose, followed by structured Args and Returns sections. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete tool with two well-documented parameters and no output schema, the description adequately covers purpose, inputs, and return value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed parameter descriptions. The description repeats parameter names but adds no new meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Delete' and resource 'custom sticker from a server', distinguishing it from other delete tools for different resources like channels or emojis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives (e.g., discord_delete_emoji). The description is purely functional without context for decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description mentions a 'confirmation of deletion' return value, adding some behavioral context. However, annotations already indicate destructive and idempotent hints; the description does not elaborate on side effects or authorization beyond schema defaults.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: two short paragraphs with clear structure. The purpose is stated first, followed by parameters and return value. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete operation with only one parameter and no output schema, the description fully covers what the tool does and what it returns. It is complete given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema provides full coverage of webhook_id with pattern and description. The description merely restates 'Discord webhook ID' without adding new semantic information, so baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete a webhook') using a specific verb and resource. It distinguishes itself from sibling tools like 'create', 'edit', and 'list' webhooks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like editing or creating a webhook. While the delete context is straightforward, the description lacks criteria or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate idempotent and non-destructive, but description lacks additional behavioral context like permissions or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Structured with Args and Returns, but could be more concise; the parameter list is somewhat lengthy for a description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and vague return statement; missing preconditions or error handling; complexity suggests more detail needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is low (22%), but description enumerates all parameters with basic types, compensating partially; nested object schemas are in schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it edits an existing auto moderation rule, distinguishing it from sibling create and delete tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use vs alternatives, but context implies use when rule exists and needs modification; sibling tools for create/delete/list are available.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate idempotentHint=true (repeatable) and destructiveHint=false, which the description implicitly supports. It adds critical behavioral context: 'WARNING: This REPLACES all existing tags! To keep existing tags, first use discord_get_channel...' This disclosure goes beyond the schema and annotations, though other side effects (e.g., permission requirements, channel type constraints) are not mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear 'Args' and 'Returns' sections. The first sentence establishes purpose immediately. While the available_tags section is verbose, it is justified given the complexity of that parameter. Overall, it is appropriately sized and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately covers the tool's behavior given the rich schema (100% parameter coverage) and annotations. However, without an output schema, the return value is vaguely described as 'Updated channel details.' It lacks guidance on which parameters apply to which channel types (e.g., bitrate only for voice) and does not mention error handling or validation constraints beyond schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear descriptions, so baseline is 3. The description adds substantial value beyond the schema by explaining nuanced usage, such as 'use 'none' to remove' on parent_id and default_reaction_emoji, and the detailed warning about tag replacement with sub-property explanations. This compensates for the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Edit a channel's properties including name, topic, category, position, and more.' This uses a specific verb ('Edit') and resource ('channel's properties'), and lists concrete examples. It differentiates from sibling edit tools like discord_edit_message or discord_edit_role by focusing on channel properties.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description only lists parameters but provides no guidance on when to use this tool versus alternatives. For example, it doesn't mention situations where editing channel properties is appropriate versus using other tools like discord_set_channel_permissions or discord_move_member. No explicit when/when-not reasoning is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate idempotent, write, and non-destructive behavior. The description adds that it returns updated server details but lacks information about required permissions, partial update behavior, or effects on unmentioned settings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The initial sentence is concise, but the arg list duplicates the input schema, making it longer than necessary. Could be more efficient by directing users to the schema for parameter details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 8 parameters, a nested object, and no output schema, the description covers basic purpose and return type but lacks details on validation, partial updates, and response structure. Adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema fully describes each parameter. The description repeats parameter names and types but does not add meaningful semantic details beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Edit server settings' with verb and resource, and lists example fields (name, verification level, system channel). Distinguishes from sibling tools like discord_edit_channel and discord_edit_role, which edit different resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for editing guild settings but does not explicitly state when to use this tool versus alternatives or provide exclusions. Context from sibling names helps, but no direct guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=false, idempotentHint=true, destructiveHint=false. The description adds no further behavioral details (e.g., whether content is fully replaced or appended). It does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is brief and well-structured, with a clear single sentence followed by Args and Returns. No unnecessary information, though the Args list is redundant with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the Returns line provides minimal confirmation but lacks error handling or prerequisites (e.g., message must be from bot). Adequate for a simple tool but leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for all parameters. The description repeats the content max length but adds no new semantics beyond the schema. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Edit a message sent by the bot', specifying the action and resource. The title confirms the purpose, and it distinguishes from sibling tools like discord_send_message and discord_delete_message.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool only edits bot-sent messages but does not explicitly state when to use it versus alternatives (e.g., sending a new message or deleting). No direct comparisons or exclusion criteria are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate non-destructive, idempotent write operation. The description adds context about returning updated configuration and the purpose of prompts. No contradictions or missing behavioral traits beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact (approx. 100 words), front-loaded with purpose, then explanatory sentences, then bulleted args, then return statement. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description mentions the return type. It covers the main aspects of the tool, though it could briefly note that existing prompts require IDs for updates (covered in schema). Overall, it is sufficiently complete for a tool with rich schema annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions. The description provides a high-level summary of parameters but does not add significant meaning beyond what the schema already offers, meeting the baseline expectation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The tool name and description clearly state it edits server onboarding. It explains what onboarding entails (prompts/questions, role/channel assignment) and distinguishes from sibling tools like discord_get_onboarding and discord_setup_onboarding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies editing existing onboarding but does not explicitly state when to use this versus alternatives (e.g., discord_setup_onboarding for initial setup) or provide conditions like requiring existing onboarding configuration.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses that permissions replace existing values and returns updated role details. Annotations already indicate idempotence and non-destructiveness, and the description adds context about permission replacement. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: purpose first, then a helpful permission reference, then arg list. It is front-loaded but could be slightly more concise by reducing the permission list or integrating arg descriptions more succinctly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters (2 required), no output schema, and good annotations, the description covers all parameters and notes the return type. It adequately informs usage for a mutation tool, though it lacks mention of error cases or validation behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by listing common permission names, explaining color format with an example decimal, and providing permission examples. This goes beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool edits a role's properties (name, color, permissions). The verb 'Edit' and resource 'role' are specific. However, it does not differentiate from sibling tools like discord_create_role or discord_edit_channel, though the name itself provides clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool vs alternatives such as discord_create_role or discord_set_role_positions. No prerequisites, context, or when-not-to-use information is provided, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already convey idempotentHint=true, readOnlyHint=false, destructiveHint=false. The description adds that it returns 'Updated webhook details', but otherwise does not elaborate on side effects or permissions. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise: one sentence for purpose, a clean args list, and a returns line. No superfluous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the return value, and the schema covers all parameters. Given the tool's simplicity and the presence of annotations, little else is needed. Minor gaps: no mention of error cases or permission requirements, but these are not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with complete descriptions for all three parameters. The description merely repeats the parameter names and purposes without adding further semantics or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states 'Edit an existing webhook', clearly specifying the verb (edit) and resource (webhook). Among sibling tools (create, delete, list), this uniquely identifies the tool's function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives (e.g., discord_create_webhook, discord_edit_channel). No prerequisites or exclusions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate non-read-only, idempotent, open world, and non-destructive. The description adds meaningful context such as required permissions and prerequisite (Community features), plus return type ('Updated welcome screen settings'), which goes beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear main sentence, a prerequisite line, a bulleted Args list, and a Returns line. It is mostly concise but the Args section repeats schema information, making it slightly longer than necessary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 parameters, 1 required), no output schema, and moderate annotations, the description covers prerequisites, permissions, parameter details, and return value. It is complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the description does not need to add much. The description restates parameter info in a structured list, adding minor formatting details but essentially duplicating the schema. This is adequate but not extra valuable.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Edit the welcome screen configuration for a server.' This is a specific verb-resource combination and distinguishes from sibling tools like discord_get_welcome_screen and other edit tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides usage context: requires Community features and MANAGE_GUILD permission. However, it does not mention when not to use it or suggest alternatives, though the sibling list includes get and other edit tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds a list of common action types and general content, but does not disclose additional behavioral traits like data freshness, rate limits, or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with purpose. The list of action types is useful but somewhat lengthy; a summary or reference could improve conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description partially covers return data (action, user, target, changes) but omits pagination, permissions, and rate limit context. Annotations help but more detail would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all parameters with descriptions (coverage 100%). The description adds value by listing common action type codes, but there is a contradiction: description says limit default is 20, while schema says 50. This inconsistency reduces clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves audit logs for a server with the verb 'Get' and resource 'audit log'. It uniquely identifies this functionality among siblings, as no other sibling tool focuses on audit logs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for viewing audit logs but lacks explicit guidance on when to use this tool versus alternatives, such as when to filter by user/action or how it differs from other log retrieval methods.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds only 'Get details' which aligns but provides no additional behavioral context (e.g., auth needs, rate limits, or data scope).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise docstring format with Args/Returns. First sentence is clear. Could be slightly more concise by omitting docstring style, but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given simple get operation, high schema coverage, and complete annotations, description covers essential usage. No output schema, but return type is implied. Adequately complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers 100% of parameters with descriptions. Description repeats parameter info and notes default format, which is already in schema. No significant new semantics beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get details of a specific auto moderation rule.' The verb 'get' and resource 'automod rule' are specific. The 'specific' qualifier distinguishes it from list, create, edit, and delete siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage (retrieve a single rule by ID) but no explicit guidance on when to use versus discord_list_automod_rules or other siblings. No exclusion or alternatives mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, establishing safety. The description adds no additional behavioral context beyond what schema provides, but does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is extremely concise: one main sentence, a list of arguments, and a returns note. No unnecessary words or redundancy, earning its place efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with well-annotated safety and no output schema, the description covers the main purpose, parameters, and return format adequately. However, it omits error handling or prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and schema descriptions cover both parameters thoroughly. The description repeats this information almost verbatim, adding no new semantic value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves detailed information about a specific channel, using the verb 'Get' and naming the resource 'channel'. It distinguishes well from siblings like discord_get_channel_permissions and discord_get_guild.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as discord_get_channel_permissions or discord_get_messages. The description does not mention exclusions or preferred contexts.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is consistent with annotations (readOnlyHint=true, destructiveHint=false, idempotentHint=true), stating it retrieves permission overrides. It adds the return type (list of overrides with allow/deny per role/member), which provides useful context beyond annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a clear purpose sentence followed by Args and Returns sections. Every sentence adds value, and there is no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with no output schema, the description adequately explains the return value (list of permission overrides). Annotations cover behavioral safety, and parameters are fully covered by schema and description. The tool's context is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so both parameters are documented in the schema. The description mentions both parameters and adds that response_format defaults to 'json', but the schema already includes a default value, so the added value is minimal. Baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get all permission overrides for a channel.' The verb 'get' and resource 'permission overrides for a channel' are specific, distinguishing it from sibling tools like discord_set_channel_permissions and discord_remove_channel_permissions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. Usage is implied by the verb 'get', but no direct guidance on when not to use or references to sibling tools are provided. The sibling list exists but is not referenced in the description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description confirms it's a read operation and lists return items, but does not disclose permission requirements, rate limits, or behavior when guild is not a community.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and well-structured: first line states purpose, then a bullet list of examples/args, and a return summary. No fluff or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description must detail return structure. It only vaguely says 'community settings including channels and features' without specifying field names or types. Missing error cases (e.g., guild not found, community not enabled).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover both parameters (guild_id and response_format) completely. The function description adds the default value for response_format and clarifies the purpose of markdown vs json, providing marginal extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The name and description clearly state this tool retrieves community settings for a server, specifying it shows rules channel, updates channel, and other community-related settings. It is distinct from siblings like discord_get_guild or discord_get_onboarding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this over other guild-related tools such as discord_get_guild, discord_get_onboarding, or discord_get_welcome_screen. No prerequisites or limitations are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already convey safety. Description adds value by listing return fields (name, member count, owner, icon). No behavioral contradictions or missing critical details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: one sentence for purpose, bullet list for args and returns. Front-loaded with the primary action. No superfluous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with full schema and annotations, the description covers purpose, parameters, and return fields. Lacks error handling details (e.g., invalid guild_id) but overall sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for both parameters. Description's args section merely repeats schema content, providing no additional meaning beyond what is already documented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states 'Get detailed information about a specific Discord server.' The verb 'Get' and resource 'Discord server' are specific and distinct from sibling tools like discord_get_channel or discord_get_member.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like discord_get_channel or discord_list_guilds. Usage is implied by the tool name and description but lacks explicit 'when-not-to-use' or alternative suggestions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds value by summarizing the return fields (username, nickname, roles, join date), providing context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured with separate Args and Returns sections. Every sentence contributes essential information without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adequately covers what the tool does, required parameters, and return fields. However, it omits potential edge cases (e.g., error handling for non-existent member), which would make it more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description repeats and slightly extends the schema descriptions (e.g., adding default for response_format), but does not significantly add new meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get detailed information about a specific member,' specifying the action (get) and resource (member). It distinguishes from sibling tools like discord_list_members by focusing on a single member via required guild_id and user_id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives, but the purpose is clear and the required parameters (guild_id, user_id) imply it is for a specific member. Sibling tool names provide implicit differentiation.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds the return format (list with content, author, timestamp, attachments) and defaults, going beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a well-structured docstring: a single-line purpose, followed by args list and returns. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All parameters and return values are covered, but there is no explanation of pagination behavior or edge cases (e.g., using both before and after). Adequate for moderate complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description provides clear docstring explanations for each parameter (e.g., 'channel_id (string): Discord channel ID'), adding value beyond schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Retrieve messages from a Discord channel' with a specific verb and resource, differentiating it from siblings like discord_send_message, discord_edit_message, etc.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or when-not-to-use guidance is given. While it implies use for reading messages, it does not discuss alternatives like discord_get_pinned_messages or pagination strategies.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's safe and idempotent. The description adds behavioral context by specifying that it returns onboarding settings (prompts, options, default channels), which goes beyond annotations. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a title, purpose statement, parameter list, and return description. It is relatively concise, though the parameter list is redundant with the schema. Overall, efficient and front-loaded with purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 params, read-only, idempotent), the description provides sufficient context. It explains the return value at a high level, which compensates for the lack of an output schema. Does not mention permissions or rate limits, but for a GET operation, this is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters. The description repeats this info but adds a default for response_format. It does not provide additional meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves the onboarding configuration for a Discord server. It uses a specific verb ('Get') and resource ('onboarding configuration'), and the tool name distinguishes it from write counterparts like discord_setup_onboarding and discord_edit_onboarding.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what onboarding is but does not explicitly state when to use this tool versus alternatives (e.g., for editing onboarding). Usage is implied from the get operation, but no explicit guidance on exclusions or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety and idempotency. The description adds that the tool returns a list of pinned messages. However, it does not elaborate on rate limits, authorization needs, or result limit behavior. The description adds marginal value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively concise and front-loaded with the main purpose. However, the 'Args:' and 'Returns:' formatting is slightly verbose and could be streamlined. It is efficient but has minor redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with two parameters, no output schema, and clear annotations. The description covers the basic functionality, parameters, and return type. However, it lacks information about permission requirements, result limits, or whether the output is truncated. This is adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Both parameters are fully described in the input schema (100% coverage). The description restates the parameter names and types but adds only the default value for response_format, which is already present in the schema. No new semantic meaning is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves all pinned messages in a channel, specifying the exact resource and action. It distinguishes itself from sibling tools like discord_get_messages (which retrieves all messages) and discord_pin_message/unpin_message (which modify pinned state).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives, such as discord_get_messages for non-pinned messages. It lacks explicit context about typical use cases or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description complements by adding the prerequisite (Community features) and describing the return shape (settings including description and channels). This adds behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and well-structured: purpose in first sentence, then requirement, then parameter list, then return value. No unnecessary words. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 parameters, no output schema), the description is complete. It covers the purpose, prerequisite, parameters, and expected returns. Annotations cover safety and idempotency, so no gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema covers 100% of parameters with descriptions. The tool description repeats the parameter names and output format but adds no new meaning beyond what the schema provides. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Get the welcome screen configuration for a server' with a specific verb and resource. Differentiates from sibling tools like 'discord_edit_welcome_screen' by focusing on retrieval. Also notes the prerequisite (Community features), adding precision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states that the server must have Community features enabled, providing a clear prerequisite. However, it does not explicitly mention when not to use this tool or suggest alternatives like 'discord_get_community_settings' for broader community settings. Still, context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds that the reason is visible in the audit log, but doesn't elaborate on side effects like rejoin ability or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: purpose, args list, and return value in six lines, front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers basic essentials: action, arguments, return type. Lacks permission hints or error conditions, but adequate for a simple destructive tool with complete schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description merely restates the schema's parameter descriptions without adding new meaning or examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Kick a member from a Discord server' with a specific verb and resource, distinguishing it from siblings like ban, remove role, or timeout.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like discord_ban_member or discord_timeout_member; lacks context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond the destructiveHint annotation by explaining the consequence (bot loses access) and the need to re-invite. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, with a purpose sentence, consequence warning, and a brief args list. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple destructive action, the description adequately covers purpose, parameters, consequences, and return value hint. Could be slightly enhanced by mentioning the bot must be in the guild, but overall complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers 100% of parameters with clear descriptions. The description repeats this information in a different format without adding new semantic details, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool leaves a Discord server (guild) and that the bot loses access. This is specific and distinguishes it from sibling tools that act on members or channels.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes a warning about destructiveness and the need for re-invitation, but does not explicitly state when to use this tool versus alternatives like kick or ban. No comparison with siblings is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds no behavioral context beyond stating it lists rules. No extra transparency on returns, pagination, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loads the purpose, and uses a clear structure with 'Args:' and 'Returns:' sections. The 'Args:' block is slightly redundant with the schema, but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple read-only list with full schema coverage and sufficient annotations. The description mentions return type and parameters. No output schema exists, but the description notes it returns a list, which is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description only paraphrases the schema's parameter descriptions. It adds no new semantic meaning beyond what the input schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all auto moderation rules for a server', using a specific verb ('list') and resource ('auto moderation rules'), and differentiates from sibling tools like 'discord_get_automod_rule' and 'discord_create_automod_rule'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites. Usage is implied by the tool's purpose, but no direct guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds no additional behavioral context beyond what annotations provide, such as permission requirements or rate limits. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured with Args and Returns sections, making it easy to parse. It is concise with no redundant sentences, though could be slightly more streamlined.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, annotations, and full schema coverage, the description is adequate. However, it lacks mention of required permissions or behavior when no bans exist, which would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds a 'Returns' section explaining the output ('List of banned users with reasons'), which is not in the schema, providing extra context for parameter interpretation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'List all banned users in a server.' It uses a specific verb and resource, and distinguishes itself from sibling list tools like discord_list_members by specifying 'banned users'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives like discord_ban_member or discord_unban_member. It implies usage for reading bans, but lacks explicit guidance or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds useful context about returned data (id, name, type, topic, category) which aids agent understanding. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, well-structured with Args and Returns sections, and front-loads the primary action. Every sentence provides value; no extraneous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 parameters, no output schema), the description along with annotations and schema provides sufficient context for an agent to use the tool. It summarizes return fields, which compensates for lack of output schema. Minor gap: no mention of pagination or rate limits, but this is acceptable for a list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with detailed descriptions for all three parameters (type, guild_id, response_format). The tool description repeats the parameter list but does not add any additional meaning beyond what the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'List' and resource 'channels in a Discord server'. It distinguishes itself from sibling tools like discord_get_channel (single channel) and discord_create_channel (creation) by specifying a list operation. The title reinforces this purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit guidance on when to use this tool versus alternatives (e.g., discord_get_channel for details, discord_list_webhooks for webhooks). Usage is implied through the description, but no when-not-to-use or comparisons are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds the return format (list with name, ID, animated) but no additional behavioral details like pagination or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a clear structure (purpose, args, returns). It is front-loaded and efficient, though the 'Args:' and 'Returns:' style could be slightly more terse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with two parameters and no output schema, the description adequately explains the purpose, parameters, and return values. It covers what an agent needs to know, though it could mention that only custom emojis are listed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, the schema already describes both parameters thoroughly. The description repeats the parameter meanings but adds no new semantic information beyond what is in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all custom emojis in a server' with a specific verb and resource. It distinguishes from sibling tools like discord_create_emoji and discord_list_stickers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit guidance on when to use this tool versus alternatives. Usage is implied but no exclusions or context are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, assuring safety. The description adds value by specifying the return structure (list of events with fields). No contradictions, and it explains behavior beyond annotations adequately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise: one sentence for purpose, followed by bullet-pointed args and returns. Every sentence is useful, and it is front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list tool with good annotations, the description covers purpose, parameters, and return fields. However, it does not mention pagination, limits, or prerequisites (e.g., permissions). It is mostly complete but has minor gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Given 100% schema coverage, the description adds minimal value. It repeats parameter names and types but lacks details like default values or format descriptions that the schema already provides. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all scheduled events in a server' with a specific verb and resource. It distinguishes from siblings like discord_create_event and discord_delete_event by focusing on listing. The return fields (name, time, location, status) are also specified.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide explicit when-to-use or when-not-to-use guidance. There are no alternatives mentioned, and prerequisites (e.g., permissions) are not discussed. For a simple list tool, the usage is implied but not instructed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, idempotentHint=true, etc. The description adds return field details but no additional behavioral context (e.g., pagination, rate limits). With annotations covering safety, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (4 lines), front-loaded with purpose, then return info and parameter. Every sentence adds value with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema. Annotations cover safety. The description adequately explains return structure and parameter, making it complete for an agent to use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter (response_format) with 100% schema coverage. The description restates the enum options and default value, adding little beyond the schema. Baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists all Discord servers (guilds) the bot has access to, and specifies the returned information (server names, IDs, member counts, owner info). This distinguishes it from sibling tools that list other entities like channels or members.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for getting an overview of available guilds but does not explicitly state when to use or avoid alternative tools. Given the many sibling tools for specific CRUD operations on guilds, some guidance would help.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, indicating a safe read operation. The description adds the return format details (code, uses, max uses, expiration) beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, uses a clear Args/Returns structure, and contains no superfluous information. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list tool with two parameters and no output schema, the description sufficiently explains functionality, parameters, and return format. Annotations cover behavioral safety.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description essentially restates the schema's parameter descriptions. It adds clarity but does not provide additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List all active invites in a server' with a specific verb and resource. It distinguishes from sibling tools like discord_create_invite and discord_delete_invite.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool vs alternatives, but it is implied as a read-only listing operation. No exclusions or alternative tool names are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false. The description adds that the tool returns a list of members with specific fields (username, nickname, roles, join date), providing context beyond the annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exceptionally concise: one sentence for purpose, followed by a clear parameter list. Every word earns its place, no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description mentions the return fields (username, nickname, roles, join date). It covers pagination via the 'after' parameter. For a simple list operation with full schema coverage and clear annotations, this is nearly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents all parameters. The description's 'Args' section largely repeats schema descriptions (e.g., 'Discord server/guild ID' for guild_id) without adding significant new meaning. The baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'List members in a Discord server', which is a specific verb+resource. It distinguishes from sibling tools like discord_get_member (single member) and discord_list_channels or discord_list_roles (different resources).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as discord_get_member or discord_list_guilds. There is no mention of use cases, prerequisites, or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.