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

With no annotations provided, the description carries full burden but only states the basic action without disclosing behavioral traits. It doesn't mention whether this requires specific permissions, if drafts are saved automatically, what happens on failure, or if there are rate limits - all important for a creation tool.

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 a single, efficient sentence that immediately conveys the core functionality without any wasted words. It's appropriately sized for a straightforward creation tool and front-loads the essential 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 creation tool with no annotations and no output schema, the description is insufficient. It doesn't explain what happens after creation (e.g., returns draft ID, success confirmation), error conditions, or how this interacts with other email operations. The context demands more completeness for effective agent 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 description coverage is 100%, so all parameters are documented in the schema. The description adds no additional parameter information beyond what the schema already provides, maintaining the baseline score of 3 for adequate but not enhanced parameter documentation.

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 a draft email') and resource ('in the Drafts folder'), making the purpose immediately understandable. However, it doesn't differentiate from sibling 'create_reply_draft', which creates a draft reply rather than a new draft email from scratch.

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 about when to use this tool versus alternatives like 'create_reply_draft' for replying to existing messages or 'list_folders' to verify the Drafts folder exists. The description assumes context without stating prerequisites 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?

No annotations are provided, so the description carries full burden. It mentions creating a draft and setting headers, but doesn't disclose behavioral traits such as whether this requires specific permissions, if drafts are saved automatically, error handling for invalid UIDs, or rate limits. The description is minimal and misses key operational details for a mutation tool.

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 two sentences that directly state the tool's function and key behavior (setting headers). It's front-loaded with the main purpose, though it could be slightly more structured by explicitly separating purpose from technical 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?

Given this is a mutation tool with no annotations and no output schema, the description is incomplete. It lacks information on what the tool returns (e.g., draft ID, success status), error conditions, or how it interacts with other tools like 'list_messages'. For a tool with 5 parameters and complex email threading behavior, more context is 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 description coverage is 100%, so the schema fully documents all 5 parameters. The description adds no additional meaning beyond what's in the schema (e.g., it doesn't explain parameter interactions or provide examples). Baseline score of 3 is appropriate as the schema handles parameter documentation adequately.

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 a reply draft') and resource ('on an existing email thread'), with specific details about finding messages by UID and setting headers. It distinguishes from 'create_draft' by specifying this is for replies, though it doesn't explicitly contrast with other siblings like 'mark_message' or 'move_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 usage by mentioning it finds messages by UID and sets headers for threading, suggesting it's for replying to existing emails. However, it lacks explicit guidance on when to use this versus alternatives like 'create_draft' for new emails or other sibling tools, and doesn't mention prerequisites 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the two deletion behaviors (move to Trash vs. permanent deletion) which is useful, but doesn't mention important aspects like whether deletion is reversible, what permissions are required, whether it affects other messages, or what happens on success/failure. For a destructive operation with zero annotation coverage, this leaves significant gaps.

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 a single, efficient sentence that communicates the core functionality and key behavioral distinction. Every word earns its place with zero redundancy or unnecessary elaboration. It's appropriately sized for the tool's complexity.

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 this is a destructive operation with no annotations and no output schema, the description should do more to explain behavioral implications and expected outcomes. While it covers the basic action and deletion modes adequately, it lacks information about reversibility, error conditions, or what constitutes successful deletion. The 100% schema coverage helps but doesn't compensate for the behavioral 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 description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds marginal value by hinting at the 'permanent' parameter's effect ('permanently delete'), but doesn't provide additional semantic context beyond what's in the schema descriptions. This meets the baseline for high 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?

The description clearly states the specific action ('Delete a message') and distinguishes between two deletion modes ('move to Trash or permanently delete'), which differentiates it from siblings like move_message (which moves between folders) or mark_message (which changes flags). The verb+resource combination is precise and unambiguous.

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 context by mentioning the two deletion modes, but doesn't explicitly state when to use this tool versus alternatives like move_message (for moving to folders other than Trash) or mark_message (for marking as deleted without removal). No prerequisites or exclusions are provided, leaving the agent to infer appropriate usage scenarios.

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?

No annotations are provided, so the description carries the full burden. It discloses the return content ('headers and text body') and a preference ('prefers plain text'), which is useful behavioral context. However, it doesn't mention error handling (e.g., what happens if UID is invalid), performance aspects, or authentication 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 a single, efficient sentence that front-loads the core purpose and includes key behavioral details (return content and text preference). Every word earns its place with 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?

For a read-only tool with no annotations and no output schema, the description provides adequate basics (purpose, return content). However, it lacks details on error cases, output structure beyond 'headers and text body', or how the 'prefers plain text' behavior works, leaving some gaps for an agent to use it effectively.

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 fully documents both parameters (folder and uid). The description doesn't add any parameter-specific details beyond what the schema provides, such as explaining UID format or folder naming conventions. Baseline 3 is appropriate when the schema does the heavy lifting.

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 specific action ('Fetch'), resource ('a single email'), and key identifier ('by UID'). It distinguishes from siblings like list_messages (which lists multiple) and search_messages (which searches by criteria rather than fetching by UID).

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 context by specifying 'by UID', suggesting this tool is for retrieving a known message rather than searching or listing. However, it doesn't explicitly state when to use alternatives like list_messages for browsing or search_messages for finding messages by content.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool lists folders but doesn't describe any behavioral traits: it doesn't specify if this is a read-only operation, whether it requires authentication, how results are returned (e.g., pagination, format), or potential errors. For a tool with zero annotation coverage, this leaves significant gaps in understanding its 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 a single, efficient sentence that directly states the tool's function without unnecessary words. It is front-loaded with the core action and resource, making it easy to parse. Every part of the sentence earns its place by conveying essential 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?

Given the lack of annotations and output schema, the description is incomplete for effective tool use. It doesn't explain what the tool returns (e.g., folder names, IDs, hierarchy), any limitations (e.g., only top-level folders), or error conditions. For a tool with no structured data to supplement it, the description should provide more context to guide the agent.

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 has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately doesn't discuss parameters, focusing instead on the tool's purpose. This meets the baseline for tools with no parameters, as there's nothing to compensate for beyond what the schema already indicates.

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') and the resource ('IMAP mailbox folders'), making the purpose immediately understandable. It doesn't explicitly distinguish from siblings like 'list_messages' (which lists messages rather than folders), but the resource specificity provides some implicit differentiation. The description avoids tautology by not just restating the tool name.

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. It doesn't mention prerequisites (e.g., needing an active IMAP connection), exclusions, or comparisons to sibling tools like 'list_messages' or 'search_messages'. The agent must infer usage context solely from the tool name and description without explicit direction.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool lists messages and defaults to INBOX, but lacks critical details such as whether this is a read-only operation, how 'recent' is defined, pagination behavior, error conditions, or authentication requirements. For a tool with zero annotation coverage, this is insufficient.

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 and front-loaded: a single sentence efficiently conveys the core action, resource, returned fields, and default behavior. Every word earns its place with no redundancy or unnecessary elaboration, making it easy for an agent to parse quickly.

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 lack of annotations and output schema, the description is incomplete for a tool that interacts with message data. It doesn't explain what 'recent' means, the format of returned messages, error handling, or how it differs from siblings like 'search_messages'. For a read operation with no structured output documentation, more context is 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?

The schema description coverage is 100%, so the schema fully documents both parameters (folder and limit). The description adds minimal value by mentioning the default folder is INBOX, which is already in the schema's default field. It doesn't provide additional context like folder path examples or limit usage scenarios beyond what the schema offers.

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's purpose: 'List recent messages in a folder' specifies the verb (list) and resource (messages), and 'with subject, from, date' indicates the returned fields. However, it doesn't explicitly differentiate from sibling tools like 'search_messages' or 'get_message', which prevents a score of 5.

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 minimal usage guidance: it mentions the default folder is INBOX, but offers no advice on when to use this tool versus alternatives like 'search_messages' or 'get_message'. There's no mention of prerequisites, exclusions, or comparative contexts, leaving the agent with little direction.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool modifies flags, implying mutation, but doesn't cover critical aspects like required permissions, side effects (e.g., if changes are reversible), error handling, or response format. The examples ('read/unread', 'flag/unflag') add some context but are insufficient for a mutation tool with zero annotation coverage.

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 a single, efficient sentence that front-loads the core purpose with clarifying examples. Every word earns its place, avoiding redundancy or fluff, making it easy to parse quickly.

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 this is a mutation tool with no annotations and no output schema, the description is incomplete. It lacks details on behavioral traits (e.g., permissions, side effects), output values, and usage guidelines, which are critical for an agent to invoke it correctly. The high schema coverage helps with parameters, but overall context is inadequate.

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 fully documents all four parameters. The description adds minimal value beyond the schema by hinting at flag examples ('\\Seen', '\\Flagged') and the tool's purpose, but it doesn't explain parameter interactions (e.g., how 'action' affects 'flags') or provide usage semantics. Baseline 3 is appropriate as the schema does the heavy lifting.

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's purpose with a specific verb ('Set or remove') and resource ('flags on a message'), including examples ('mark as read/unread, flag/unflag'). It distinguishes from siblings like 'delete_message' or 'move_message' by focusing on flag manipulation rather than deletion or relocation, though it doesn't explicitly differentiate from all 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a message UID), exclusions, or comparisons with sibling tools like 'get_message' for viewing flags or 'search_messages' for finding flagged messages, leaving usage context implied at best.

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?

No annotations are provided, so the description carries full burden. 'Move' implies a mutation, but it doesn't disclose behavioral traits like whether this requires specific permissions, if the operation is reversible, what happens to the original message (e.g., deletion from source), or error conditions (e.g., invalid UID). The description is minimal and lacks crucial context for a mutation tool.

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 a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, making it easy to parse quickly. Every word earns its place 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?

Given the tool's complexity (mutation with 3 parameters), lack of annotations, and no output schema, the description is incomplete. It should cover more behavioral aspects (e.g., permissions, reversibility) and usage context to compensate for missing structured data, but it provides only a basic statement of purpose.

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 all parameters (folder, uid, destination) with descriptions. The description adds no additional meaning beyond what's in the schema, such as explaining folder path formats or UID sourcing. Baseline 3 is appropriate when schema does the heavy lifting.

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 ('move') and resource ('a message'), specifying the target ('to another folder'). It distinguishes from siblings like delete_message (destructive) and get_message (read-only), but doesn't explicitly contrast with mark_message (which modifies flags rather than location).

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. It doesn't mention prerequisites (e.g., needing message UID from list_messages), exclusions (e.g., cannot move to non-existent folders), or comparisons to similar tools like mark_message for organizing messages differently.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions search criteria but doesn't cover important aspects like whether this is a read-only operation, potential rate limits, authentication needs, error handling, or the format of returned results (e.g., pagination). This is inadequate for a search tool with no annotation support.

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 a single, efficient sentence that front-loads the core purpose and lists key criteria without unnecessary words. Every part of it contributes directly to understanding the tool's function.

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 a search tool with 6 parameters, no annotations, and no output schema, the description is incomplete. It lacks details on behavioral traits (e.g., safety, performance), output format, and usage context relative to siblings, making it insufficient for an agent to use the tool effectively without additional inference.

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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description lists the criteria (subject, from, since date, unseen only), which aligns with the schema but doesn't add meaningful semantic context beyond what's in the parameter descriptions. This meets the baseline for high 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?

The description clearly states the tool's purpose with a specific verb ('search') and resource ('messages in a folder'), and it lists the search criteria. However, it doesn't explicitly distinguish this tool from sibling tools like 'list_messages' or 'get_message', which might offer similar functionality.

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. It doesn't mention sibling tools like 'list_messages' (which might list without filtering) or 'get_message' (which might retrieve a single message), leaving the agent to infer usage context.

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