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

The description discloses idempotence, a key behavioral trait. However, beyond that, it does not mention any side effects, authorization requirements, or whether it mutates state. With no annotations, the description could provide more context on the tool's safety profile.

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?

Two sentences, zero waste. The description is front-loaded and efficiently conveys the essential information without superfluous text.

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 (1 param, no output schema, no annotations), the description covers the core purpose and idempotence. It could be considered complete, though adding a note about the return value or the effect of consecutive calls would enhance 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?

The schema description coverage is 0%, and the tool description adds no meaning to the single parameter 'post_id' beyond what the schema provides (integer constraints). The parameter is self-explanatory given the tool's purpose, but the description misses an opportunity to clarify how to obtain the post_id or its context.

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 'acknowledge' and the resource 'post', and adds the clarifying context 'read receipt'. This succinctly distinguishes it from sibling tools like 'post' (create) and 'read_posts' (read).

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 (e.g., after reading a post). The usage is implied by 'acknowledge a post (read receipt)', but there is no mention of when not to use it or which sibling tools serve related purposes.

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 provided, so description carries burden. Adds important info: token/config shown once and must be handed off. Lacks details on side effects, idempotency, or restoration.

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?

Two sentences packed with essential info. Slightly dense but efficiently conveys purpose and key notes.

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 purpose, usage, and return value (setup object). Missing error conditions and distinction between create vs re-token scenarios. With many siblings, the description is adequate but not thorough.

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 0% schema description coverage, description adds meaning for lane and is_admin (e.g., 'does not partition anything'). Does not describe participant_name or kind beyond schema 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?

Clear verb 'create (or re-token)' and specific resource 'teammate participant' with detailed output; distinguishes from siblings like admin_revoke and admin_rotate.

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 'Project-admin only' and provides context for optional params (lane, is_admin). Does not mention when not to use or alternative tools, but the purpose is unique among siblings.

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. It discloses that the operation is reversible (history preserved, lockout until re-granted/rotated) and returns a count. It also notes the behavior when the participant has no active tokens. This is good transparency, though rate limits or permission details beyond 'admin' 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 two sentences with no extraneous information. The first sentence states the action and scope, the second explains effects and return value. It is front-loaded and 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 single-parameter tool with no output schema, the description covers the action, scope, behavioral effects (history preservation, lockout), and return value. It also addresses the edge case of 0 count. It lacks explicit mention of whether multiple tokens are handled, but 'token(s)' implies plural. Overall, it is mostly 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 schema has 0% parameter description coverage, so the description must compensate. It explains the parameter as 'by participant name' linking to 'teammate' in the project. However, it does not specify the format (e.g., username vs email) or constraints beyond min/max length. This is adequate but minimal added 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 the tool revokes active tokens of a teammate by participant name within the project. It uses a specific verb 'revoke' and resource 'token(s)', and distinguishes from siblings like 'admin_provision' and 'admin_rotate' by being explicitly a revocation action.

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 specifies that the tool is 'Project-admin only' and scoped to the current project. It explains the effect (lockout until re-granted or rotated) and the return value, providing clear context. However, it does not explicitly compare to alternatives like 'admin_rotate' or state 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?

With no annotations, the description effectively discloses the atomic transaction (no lockout gap), the output (new token and setup config), and the one-time display constraint. It adds critical behavioral context beyond the schema.

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?

Two sentences, no filler, essential information front-loaded (authorization, operation, result). Highly 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?

For a single-parameter tool with no output schema or annotations, the description covers authorization, atomic behavior, and return handling. Some missing details like prerequisites or error conditions, but largely 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?

The description mentions 'by participant name' for the only parameter, but schema coverage is 0% and the description does not explicitly detail the parameter's meaning or constraints 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 tool rotates a teammate's token, specifying it's project-admin only and distinguishes from siblings like admin_revoke and admin_provision by describing the atomic mint-then-revoke operation.

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?

It explicitly says 'Project-admin only' and implies when to use (rotation without lockout gap) but lacks explicit alternatives or when-not-to-use guidance given the many sibling admin 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?

With no annotations provided, the description bears full responsibility for behavioral transparency. It discloses atomicity, collision-freedom, and formatted return but omits details on error handling, side effects (e.g., whether the sequence must pre-exist), or response structure beyond 'formatted id'.

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?

Two concise sentences front-load the core action and key properties. No wasted 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 lack of annotations and output schema, the description covers core behavior but leaves gaps: no clarification on what 'formatted id' looks like, no mention of the optional 'note' parameter, and no error scenarios. 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 0%, meaning no parameter descriptions in the schema. The tool description does not explain the 'sequence' constraints (minLength, pattern) or the 'note' parameter's purpose, leaving the agent without additional semantic meaning beyond raw 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 tool atomically allocates the next number for a sequence, uses a specific verb 'allocate', and gives an example use case (ADR/migration). It distinguishes from siblings by claiming to be 'the sole source of the number', implying uniqueness compared to tools like 'seed_sequence' or 'latest_claims'.

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 some usage context via the example and emphasizes collision-free allocation, but it does not explicitly state when to use this tool versus alternatives like 'lease', 'register', or 'ack'. There is no 'when-not-to-use' guidance or mention of 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?

No annotations are provided, so the description carries full behavioral weight. It reveals that the token is delivered directly to the invitee, not through the admin, and that redemption happens at '/join'. It also explains the 'participant_name' behavior. Missing details like whether the action is reversible or rate-limited, but the key behavioral traits are covered.

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?

Three sentences, no fluff. Critical info is front-loaded: who can use, what it creates, key behavior. 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?

The tool has 6 parameters, no annotations, and no output schema. The description covers the main purpose and a key behavioral trait but omits parameter details and return values. For a tool with this complexity, the description is insufficient for an agent to invoke correctly without additional knowledge.

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 has 6 parameters, but the description only explains 'participant_name'. It does not mention 'kind', 'lane', 'is_admin', 'uses', or 'ttl_hours'. With 0% schema description coverage, the description fails to compensate for the missing parameter documentation, leaving the agent without guidance on most parameters.

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 creates a project invite and a copy-paste onboarding prompt. It specifies the action ('mint'), resource ('project invite'), and scope ('project-admin only'). It distinguishes from sibling tools like 'claim' and 'register' by indicating this is for inviting others, not self-claiming.

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 explicitly notes 'Project-admin only', setting the authorized user. It advises to omit 'participant_name' to let the invitee choose their own name. However, it does not explicitly mention when not to use or suggest alternatives, though the context implies it's for inviting teammates.

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?

Without annotations, the description must fully disclose behavior. It implies a read-only operation with 'latest claimed number', but does not explain what 'claimed' means, potential side effects, or performance characteristics beyond 'fast'.

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 (8 words) and front-loaded with the key action and result. Every word earns its place.

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 0 parameters and no output schema, the description provides the core purpose but lacks details on result format or how sequences are identified. It is minimally complete for a simple tool but could be more thorough.

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?

There are 0 parameters, so the baseline is 4. The description adds meaning by explaining the output (latest claimed numbers per sequence) and context (collision audit), which is valuable beyond the empty 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 returns 'latest claimed number per sequence' and adds the use case 'fast collision audit'. It distinguishes itself from siblings like 'claim' or 'who_holds' by focusing on the 'latest' and 'per sequence' aspect.

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. The phrase 'fast collision audit' hints at a use case, but there is no direct comparison to siblings like 'who_holds' or 'claim'.

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, the description carries the burden. It discloses the advisory nature and that it returns overlapping holders, but does not explain side effects like persistence or behavior with ttl. Some value beyond schema but gaps remain.

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 at 13 words, front-loaded with key info. However, it lacks structure like bullet points and could be slightly more verbose without losing 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, no annotations, and three parameters, the description is incomplete. It does not explain the return format, parameter effects, or lifecycle of the lease. More detail is needed for a tool managing leases.

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 0%, so the description must explain parameters. It only clarifies 'surface' as a file/path, but ignores 'ttl_seconds' and 'note'. This is insufficient for a three-parameter tool.

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 is an 'advisory lease on a surface (file/path)' and differentiates it from a hard lock. The verb 'lease' and resource 'surface' are specific. However, it could be more explicit about the action (e.g., acquiring a lease).

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 when to use it (advisory vs hard lock) through phrasing, but does not explicitly state when to use or alternatives. No guidance on when not to use or comparisons to siblings like 'claim' or 'release'.

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 alone must convey behavioral traits. It discloses the data fields returned and implicitly indicates a read-only operation by describing the output as a roster listing. However, it does not mention potential performance characteristics, rate limits, or permissions required, which would be beneficial for a more complete transparency.

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 consists of two concise sentences: the first states the purpose and output fields, the second provides a usage tip. No superfluous words, and the information 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?

Given the tool has no parameters and no output schema, the description adequately explains what the tool does and returns, and suggests a specific use case. It could be more complete by clarifying that it lists all participants without pagination or ordering, but overall it's sufficient for a simple list operation.

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 zero parameters, so schema description coverage is 100%. The description does not need to add parameter details. The baseline for 0 parameters is 4, and the description meets that standard.

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 'participants granted into THIS project (the roster)', and enumerates the fields returned (name, kind, lane, admin flag, token active). It distinguishes itself from sibling tools like admin_provision, admin_revoke, etc., by focusing on a read-only listing of participants.

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 explicitly states when to use this tool: 'Use before admin_provision to avoid creating a duplicate.' This provides clear guidance on the workflow context and gives a specific alternative action to avoid.

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 provided, but the description makes clear this is a read operation (lists sequences). It does not disclose further behavioral traits (e.g., permissions), but for a simple list tool this is sufficient.

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?

Two concise sentences. First sentence states purpose and output fields; second sentence provides usage advice. 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 tool with no parameters and no output schema, the description fully covers what it returns (fields listed) and usage context. No 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?

No parameters exist, so schema coverage is trivially 100%. Baseline for 0 parameters is 4. Description adds no param info, which is fine.

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 project sequences with specific fields (name, prefix, etc.). It distinguishes itself by advising to read instead of guessing, contrasting with sibling tools like seed_sequence.

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 tells when to use (to check existing sequences) and what to do if missing (ask before seeding). Provides actionable guidance and implies not to use seed_sequence prematurely.

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, the description carries the full burden. It conveys a read operation with filtering and a specific output feature. However, it omits traits like authorization requirements, rate limits, sorting order, or pagination behavior despite a 'limit' parameter.

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 sentence, front-loaded with the purpose, and contains no unnecessary words. Every word earns its place.

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 4 optional parameters, no output schema, and no annotations, the description covers the primary action and a notable output feature but lacks details on return format, pagination (despite limit param), ordering, or access implications. It is adequate but not fully 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 0%, so the description must compensate. It adds meaning for three parameters (status, owner, lane) by stating they are filters, but omits the 'limit' parameter entirely. The mention of 'open-blocker count' adds context not in the schema but does not cover all parameters.

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', the resource 'tasks', and the scope 'in this workspace'. It specifies two key features: filtering by status/owner/lane and inclusion of open-blocker count. This distinguishes it from sibling task mutation tools like task_create or task_assign.

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 listing filtered tasks but does not provide explicit when-to-use or when-not-to-use guidance. No alternatives among siblings are mentioned, though none seem to serve the same purpose.

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 bears full responsibility for disclosing behavioral traits. It states 'Send' which implies a mutation, but does not mention side effects (e.g., persistence, visibility), authorization needs, rate limits, or whether the action is reversible. Agents lack critical behavioral context.

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 sentence that front-loads the core action and key optional fields. It is not verbose and efficiently conveys the primary use case. Minor improvement would be adding a brief usage note, but it is already appropriately 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?

With 6 parameters, no output schema, and no annotations, the description should be more comprehensive. It only sketches the use case but omits parameter details, return value structure, error handling, and any prerequisites. The tool is moderately complex, and this description leaves significant 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 0%, so the description must add meaning. It only mentions 'subject', 'ref', and 'tag' as optional, without explaining the roles of 'to_lane', 'to_actor', 'ref', or 'tag'. The schema provides maxLength constraints but no semantic value; the description does not compensate for the gap.

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 'Send' and the resource 'attributable prose note/handoff', specifying recipients (lane and/or actor) and optional fields (subject/ref/tag). It distinguishes from siblings like 'read_posts' (reading) and 'claim' (different action), making the tool's unique role evident.

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. Siblings include 'ack', 'claim', and 'read_posts', but the description does not provide any context about when to prefer 'post' over these or any conditions for use.

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, the description discloses that filters are exact, combined with AND, and results are newest first. It does not mention pagination or rate limits, but for a query tool, the core behavior is clear.

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?

Two short sentences, each adding essential information: purpose in the first, query logic in the second. 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?

The description covers the query behavior but does not describe the return format or output schema. For a tool with 9 parameters and no output schema, more detail about the returned events 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?

The description adds that all input properties are exact-match filters combined with AND, which provides semantic context beyond the schema. However, it does not explain individual parameters, their types, or allowed values 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 queries an append-only ledger with exact filter matching, explicitly excludes semantic search, and specifies AND-combination and newest-first ordering. This distinguishes it from siblings like read_posts or search-like 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 notes that the tool does not do semantic search, implying an alternative exists, but it does not name specific sibling tools or provide explicit when-not-to-use guidance.

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, the description bears full responsibility for behavioral disclosure. The verb 'Read' clearly indicates a read-only operation with no side effects. No additional behavioral traits (e.g., auth needs, rate limits) are mentioned, but the core behavior is transparent.

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 with two short sentences. The first sets the purpose, the second adds key parameter hints. Every word earns its place; no 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?

Given 6 parameters, no output schema, and no annotations, the description covers the core purpose and two filter hints. However, it omits details on return format, pagination, and most filter parameters, leaving the tool somewhat under-specified for full 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 description coverage is 0%, so the description must compensate. It adds meaning for two parameters ('to_me' and 'unacked_only') but leaves four others (to_lane, tag, ref, limit) unexplained. This partial coverage is adequate but not complete.

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 'Read prose posts in this workspace,' specifying the action (read) and resource (prose posts). While it does not explicitly differentiate from sibling tools like 'post' (which likely creates posts), the verb 'read' makes the purpose 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 provides brief parameter hints for 'to_me' and 'unacked_only,' giving some context for filtering. However, it lacks explicit guidance on when to use this tool versus alternatives, or any exclusions for required 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?

With no annotations, the description must fully disclose behavioral traits. It mentions 'who-owns-what + liveness' but does not explain effects like overwriting previous registrations, timeout behavior, or authentication requirements. Critical behavioral details are missing.

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, front-loaded sentence that efficiently conveys the core purpose. However, it is too concise given the need for more detail, especially with 0% schema coverage and no annotations.

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 (two parameters, no output schema, no annotations) and sibling tools, the description is incomplete. It does not explain registration duration, liveness tracking, or how to deregister, leaving significant gaps for an AI 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?

Schema description coverage is 0%, so the description must add meaning. It identifies 'lane' and 'status' but provides no specifics on valid values or format beyond a vague hint about ownership and liveness. The description fails to clarify parameter semantics 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 tool announces presence in a lane with an optional status, using specific verbs and resources. However, it does not differentiate from sibling tools like 'claim' or 'who_is_active', which may have overlapping 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?

No guidance is provided on when to use this tool versus alternatives such as 'claim' for acquiring ownership or 'who_is_active' for checking presence. The description lacks any when-to-use or when-not-to instructions.

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 only states the action without revealing behavioral traits like what happens if no lease exists, whether it can release another's lease, or if it requires ownership/permissions. With no annotations, the description should carry more burden but fails to do so.

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 sentence, making it concise and front-loaded. However, it sacrifices necessary detail, so while it earns its place, it does not fully serve the tool's needs.

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, no output schema, and a single parameter, the description is inadequate. An agent would have trouble understanding the tool's preconditions, effects, and how it fits with siblings like 'lease' and 'claim'.

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 only parameter 'surface' has no schema description and the tool description does not clarify what it means (e.g., surface ID, name). 0% schema coverage means the description should compensate, but it adds no additional 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 the action ('release') and the resource ('active lease(s) on a surface'). It distinguishes from the sibling tool 'lease' by implying the opposite operation, but it does not explicitly contrast with other siblings or provide broader context.

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, prerequisites (e.g., must have an active lease), or when not to use it. The description lacks information about typical scenarios, making it hard for an agent to decide appropriately.

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, the description carries full burden. It only discloses 'Never rewinds a counter', omitting idempotency, error conditions, side effects, or whether it creates missing sequences.

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?

Single sentence plus example, no unnecessary words. Extremely concise while conveying core 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 no output schema and 0% schema coverage, the description is too minimal. It lacks return value, error handling, and complete parameter details, making it insufficient for an agent to reliably invoke the 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 0%, so description must compensate. It explains 'sequence', 'current' (offset), 'prefix' via example, but does not clarify 'pad' meaning (zero-pad length) or validate format 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 clearly states the tool initializes/seeds a sequence with a format, using specific verb and resource. It distinguishes from siblings like list_sequences by focusing on seeding rather than listing, but does not explicitly differentiate.

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. The only behavioral note is 'Never rewinds a counter', but lacks context on prerequisites (e.g., does the sequence need to exist?) or when not to use.

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 only reveals the state transition effect. It does not disclose required permissions, error states, side effects on previous owners, or return values, leaving significant behavioral 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 sentence that communicates the core action efficiently. However, it omits essential details like parameter explanations and error conditions, making it slightly under-specified.

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 two required parameters and no output schema or annotations, the description lacks information on prerequisites, error handling, return values, or behavior in invalid states, making it incomplete for safe 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?

The schema has no descriptions for parameters (0% coverage), and the tool description adds no clarification beyond 'task' context. The 'owner' parameter's format (e.g., user ID, email) is unspecified, providing minimal guidance.

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 ('Assign') and resource ('task'), and includes a state transition notation ('open/assigned → assigned'), which distinguishes it from sibling tools like 'task_create' or 'task_resolve'.

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 tasks in open or assigned states, but does not explicitly state when to use this tool over alternatives like 'claim' or 'task_block', nor does it mention 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?

Without annotations, the description carries the full burden. It discloses that the tool changes status from in_progress to blocked, which implies it is a write operation. However, it does not mention other behavioral traits like authorization requirements or whether the action is reversible.

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?

A single sentence that is front-loaded with the action and includes all key elements: the action, optional dependency, required reason, and state transition. 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 low-complexity tool with 3 parameters and no output schema, the description covers the main purpose and parameter meanings. However, it lacks details on preconditions (e.g., task must be in_progress), error handling, or return values, which would be helpful for complete understanding.

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 description explains the 'on' parameter as an optional task ID to block on, and the 'reason' parameter as a required reason. However, the required 'task_id' parameter is not explicitly described. With 0% schema description coverage, the description partially compensates but misses the chance to detail constraints like positive integer or max length.

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 marks a task blocked, specifying the state transition from in_progress to blocked. It distinguishes from sibling tools like task_start or task_resolve by indicating this is a blocking action, but does not explicitly contrast with alternatives.

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 other status-change tools (task_start, task_resolve, etc.). The description mentions optional blocking on another task but provides no context on prerequisites, such as the task needing to be in_progress first.

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, the description carries full burden. It only states the basic function and one behavioral nuance (open vs assigned). It does not disclose side effects, idempotency, error conditions, permissions, or return value—critical 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 one concise sentence, front-loaded with the action. However, it sacrifices completeness for brevity; more structure (e.g., listing key parameters or result) would improve it without being verbose.

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 4 parameters, no output schema, no annotations, and many sibling tools, the description is insufficient. It doesn't explain parameter meanings, required fields beyond title, return value, or usage context. A user would need external documentation to use this tool 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 coverage is 0% (no parameter descriptions in schema). The description only adds context for the 'owner' parameter ('if an owner is given'), leaving title, detail, and lane undocumented. The description adds minimal value beyond parameter names.

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 task' and distinguishes between open and assigned tasks based on owner presence. However, it does not explicitly differentiate from sibling tools like task_assign or task_ship, so it's clear but not fully distinct.

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 implies that to create a task with an owner, use this, but does not mention when to use task_assign for assigning existing tasks or other task verbs.

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 burden. It discloses a key behavioral effect: the task returns to 'in_progress' when no blockers remain. However, it does not mention whether the action is destructive, reversible, or requires specific permissions. The description adds some context but is incomplete.

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 short and to the point, with no unnecessary words. However, it lacks structure (e.g., bullet points) that could improve readability for an AI agent. It is concise but could be better organized.

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 (mutating state), lack of output schema, and no annotations, the description is incomplete. It does not explain what happens when blocker is omitted (resolve all?), error conditions, or return values. The many sibling tools also demand clearer differentiation.

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 0%, so the description must compensate. It mentions 'blocker(s)' but does not explain what the blocker parameter represents (e.g., blocker ID) or its format. The description adds minimal value over the schema's parameter names and types.

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 'resolve' and the resource 'task's blockers', and mentions the return to 'in_progress' state. This distinguishes it from sibling tools like task_block. However, it could be more precise about what 'resolve' entails (e.g., removing a specific blocker).

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 (e.g., task_block). The description implies usage for removing blockers but doesn't provide context or prerequisites. Given the large set of sibling tools, this is a significant gap.

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 only states the state transition, but does not disclose side effects, permissions required, reversibility, or whether it triggers any notifications or side effects. For a state-changing tool, more disclosure is needed.

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 single sentence with no unnecessary words. The core action and state change are front-loaded, making it easy to scan.

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 simple tool (one parameter, no output schema), the description minimally explains the action but omits important contextual information like return values, error behavior, prerequisites, and differentiation from similar sibling tools (e.g., task_resolve). In a large set of sibling tools, this lack of completeness could lead to incorrect tool selection.

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 0% and the description does not explain the single parameter 'task_id' beyond its name. It lacks context on what task_id refers to, how to obtain it, or any constraints. The description fails to compensate for the lack of schema 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?

Description uses specific verb 'ship' and explicitly states the state transition 'in_progress → done', clearly distinguishing it from sibling tools like task_start (which initiates a task) and task_resolve (which might resolve a task differently). The purpose is immediately clear.

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 task_resolve or other state transitions. No mention of prerequisites (e.g., task must be in in_progress state) or conditions. The description only states what it does, not when 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?

No annotations are provided, so the description carries the full burden. It discloses only the state change effect but omits any side effects, permissions required, idempotency, or safety considerations. For a mutation tool, 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 very concise (one sentence) and front-loaded with the action and state transition. It wastes no words, but could benefit from slightly more detail without becoming verbose.

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 (1 param, no output schema, no annotations), the description is minimally complete in stating the primary action. However, it lacks parameter explanation and usage guidance, leaving gaps for safe and correct invocation.

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 no parameter descriptions (0% coverage), and the description does not explain the task_id parameter at all. The schema provides constraints but no semantic meaning, leaving the agent without context for what task_id represents.

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 'Start' and resource 'task', and specifies the state transition from assigned to in_progress. This distinguishes it from sibling tools like task_create, task_assign, task_resolve, etc. However, it could be more explicit about what 'start' entails beyond the state change.

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 its siblings. It does not mention prerequisites (e.g., task must be assigned) or when not to use it (e.g., if task is already in_progress). The context is only implied by the state transition.

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?

Discloses cursor advancement as a side effect and what data is returned. No annotations provided, so description carries burden. Lacks details on idempotency, auth requirements, 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?

Single sentence is concise and front-loaded, but omits important parameter details. Could be more efficient if it included parameter hints.

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 description lacks return format details. For a composite digest, more is needed to understand the result structure. Parameter descriptions are missing entirely.

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?

Description does not mention schema parameters at all. Schema coverage is 0%, so agent gets no guidance on advance_cursor or limit.

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 it's a session-start digest returning unacked posts, active leases, and latest claim per sequence, and that it advances the cursor. This distinguishes it from sibling tools like read_posts or latest_claims.

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?

Context is clear: use at session start. However, no explicit exclusions or alternatives mentioned, though implied by the compound nature.

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, the description carries the full burden. It discloses the output (actor, project, admin flag) but does not mention side effects, authorization requirements, or rate limits. As a read-only introspection tool, this is adequate but not highly transparent.

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, concise sentence that front-loads the core purpose. Every word adds value, with zero waste 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?

Given the tool has no parameters, no output schema, and is a simple identity retrieval, the description fully explains what the agent can expect. No additional 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 tool has zero parameters and schema coverage is 100%. The description does not need to add parameter meaning, and the baseline score for no parameters is 4. No additional parameter info is required.

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 returns the resolved identity including qualified actor, project, and admin flag. It uses a specific verb ('Return') and resource ('resolved identity'), and the output details differentiate it from sibling tools like 'who_holds' or 'who_is_active'.

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 implicitly indicates usage for identity introspection but does not explicitly state when to use this tool versus alternatives. Given the context of sibling tools, the purpose is clear enough, though some guidance on when not to use could enhance 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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It indicates the tool lists 'active' leases, but omits details on result limits, sorting, permissions, or whether the operation is read-only. The return format is also unspecified, relying on inference.

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 sentence of 12 words, front-loading the action and resource. It conveys the core purpose efficiently with zero 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 tool with one optional parameter and no output schema, the description covers the core purpose but lacks details on return structure, pagination, or any behavioral constraints. It is minimally adequate but leaves several aspects unspecified.

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 has no description for the 'surface' parameter (0% coverage). The tool description adds that it is optional and filters results for one surface, which provides essential context. However, it does not clarify what a 'surface' is (e.g., ID, name) or valid values, leaving ambiguity.

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 the resource 'active advisory leases' within the workspace. It also specifies the optional filter 'for one surface', making the tool's function precise and distinguishable from sibling list tools like list_tasks or list_participants.

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 is provided. However, the resource name 'advisory leases' is unique among siblings, so context implies usage for listing leases. The optional surface filter is mentioned but no exclusions 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?

With no annotations provided, the description carries the full burden. While it mentions lane-scoping and liveness, it does not disclose whether the operation is read-only, required permissions, or potential side effects. The behavioral traits are under-specified.

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 short sentences that immediately state the purpose and a usage hint. Every word adds value, 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?

Given no output schema, no annotations, and two optional parameters, the description lacks crucial context: what constitutes a 'liveness window', how 'within_seconds' modifies results, and what the output format is. It is incomplete for an agent to reliably invoke the tool without additional knowledge.

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 0%, so the description must explain parameters. It adds meaning to 'lane' by noting scoping, but fails to explain 'within_seconds' (its range, format, or effect). Only partial parameter semantics are conveyed.

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 the resource 'actors seen within the liveness window'. It distinguishes the tool by specifying lane-scoping and hints at practical use, making it distinct from siblings like list_participants or whoami.

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 phrase 'Check before touching a shared surface' gives context for when to use the tool, but lacks explicit guidance on when not to use it or alternatives. No comparison with other sibling tools is provided.

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