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 only states that a reply is added, implying a creation operation, but fails to mention critical details such as required permissions, whether the operation is idempotent, any side effects (e.g., notifications), or the response format. This lack of transparency increases the risk of misuse.

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 efficiently conveys the tool's purpose and a usage hint. Every word serves a purpose, with no redundancy or irrelevant details. This makes it quick for an AI agent to parse and understand.

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 three parameters and no output schema, the description provides the essential purpose and usage hint. However, it omits what the tool returns (e.g., the created reply object or a success indicator), which would help the agent confirm the action's result. Given the tool's simplicity, the gap is moderate.

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 100% description coverage for all three parameters, so the schema already documents them sufficiently. The description adds no additional semantic context about the parameters, neither clarifying defaults (like author defaults to 'AI Agent') nor explaining allowed values. Under high schema coverage, a baseline score of 3 is appropriate.

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

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

The description clearly states the verb ('Add') and the resource ('reply to an annotation thread'), and provides concrete examples ('ask a clarifying question or note a finding'), making the tool's purpose clear. However, it does not explicitly distinguish this tool from similar siblings like 'add_bot_reply', which may share the same resource but differ in actor or intent.

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 gives an example of when to use the tool ('to ask a clarifying question or note a finding'), implying a conversational or investigative context. But it does not specify when not to use it, or mention alternative tools (e.g., add_bot_reply) for bot-generated replies, leaving the agent with limited guidance on tool selection.

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

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

With no annotations, the description discloses the hardcoded author fields, bot styling trigger, and idempotency check, but omits side effects or response details.

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

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

Three clear, front-loaded sentences with no waste. Each sentence adds critical 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?

Despite no output schema, the description covers purpose, constraints, and idempotency. Lacks return value details but sufficient for a simple creation tool.

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

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

Schema coverage is 100%, so baseline is 3. The description adds constraints for 'body' (paragraph limits, tone) but mostly reinforces existing schema descriptions.

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

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

The description clearly states the verb ('Post') and resource ('reply to a pin's thread'), and distinguishes itself from sibling 'add_agent_reply' by hardcoding author fields.

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 restricts usage to the /pincushion-replies flow and mentions idempotency conditions, but does not explicitly name alternative tools for generic replies.

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, disclosing that developers consume paid seats, commenters are free, and a prompt appears if the seat limit is reached. This is comprehensive for a simple add 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?

Three sentences, front-loaded with purpose, followed by role details and seat limit warning. Every sentence serves a purpose with no waste.

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

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

Given the tool's simplicity and no output schema, the description explains key outcomes (upgrade prompt). Covers roles, seat limits, and default name behavior adequately.

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

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

Schema covers all four parameters with descriptions (100% coverage). The description adds marginal value, e.g., 'name defaults to email prefix'. Baseline of 3 is appropriate.

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

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

The description clearly states 'Add a collaborator to a PinCushion project' with a specific verb (add) and resource (collaborator). It distinguishes from siblings like 'remove_member' and 'list_members' by specifying roles and seat limits.

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?

Provides guidance on when to use (adding members) and differentiates between developer (paid) and commenter (free) roles. Mentions seat limit behavior but lacks explicit exclusions or alternatives for member management.

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. It states the status transition but omits side effects, reversibility, or authorization requirements. Adequate but minimal.

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 efficient sentences, front-loaded with action and outcome. 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?

Given no output schema and no annotations, the description covers purpose, effect, and a usage hint (only approved should be implemented). Could mention prerequisite of 'open' status, but implicitly covered. Generally complete for a simple state transition 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?

Input schema has 100% coverage; description adds no additional meaning to parameters beyond what schema already provides. Baseline score is appropriate.

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

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

Clearly states the verb 'approve' on the resource 'pin', with explicit outcome of transitioning from 'open' to 'approved' status. It distinguishes from sibling tools like 'claim_pin' or 'implement_approved_pins'.

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?

Implies use before implementation via 'Only approved pins should be implemented by agents.' but lacks explicit when-not-to-use or alternatives (e.g., 'assign_pin_to_agent' or 'claim_pin').

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?

Details side effects: promotes pin, marks pending, drops trigger file; discloses integration with agent-loop.mjs and Cursor/Claude Code/Codex.

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, each adding value; front-loaded with main action.

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

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

Covers action and side effects; no output schema but return value not critical for 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?

Schema covers both params with descriptions; description adds context that pin becomes agent work.

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

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

Clearly states it assigns a pin to the local coding agent, promotes status, and triggers dispatch. Distinguishes from siblings by being the direct assign-to-agent 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?

Describes workflow but doesn't explicitly mention when not to use or alternatives.

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 fully carries the burden of behavioral disclosure. It reveals that the tool is a legacy fallback, the claimToken is valid for 7 days, and alternative behavior without the token. It does not detail success/failure responses or side effects, but the given information is sufficient for safe invocation.

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 front-loaded with 'LEGACY FALLBACK' to set immediate context. It efficiently explains the new flow before describing the tool's purpose, avoiding confusion. While slightly verbose, every sentence provides unique value, earning a score of 4 for structure and 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 the tool's complexity (6 parameters, legacy fallback scenario) and lack of output schema, the description covers the key aspects: when it applies, parameter details, and behavior edge cases. It lacks explicit return value description, but the mention of 'attach the webhook' and 'returns new flow instructions' provides sufficient context for an agent to understand the tool's effect.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds some context for claimToken (one-time, 7-day validity) and projectId (owner/editor requirement), but these details are marginal. Other parameters are adequately described in the schema, and the description does not significantly enhance understanding beyond the schema.

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

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

The description clearly identifies this as a legacy fallback tool for linking Slack installs to a Pincushion license when automatic matching fails. It specifies the action (attach webhook via claimToken and projectId) and distinguishes it from the modern auto-link flow, providing high purpose clarity.

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

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

The description explicitly states when to use this tool (only when the installer's Slack email did not match a Pincushion license at install time) and when not to use (since May 2026, auto-link is preferred). It also explains the behavior when calling without a claimToken (returns new flow instructions), offering clear usage 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?

No annotations provided so description carries full burden. It discloses the state transition and coordination purpose. Missing details on error cases (e.g., already claimed pin) but sufficient for typical use.

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 filler. Front-loaded with purpose, then state info, then workflow instructions. Every sentence 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 simple state-transition tool with no output schema, description covers purpose, workflow, and state change. Could mention handling of already claimed pins, but overall adequate.

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

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

Schema coverage is 100% with descriptions for both parameters. Description does not add extra meaning beyond what schema provides, so baseline 3.

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

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

Description clearly states the tool claims an actionable pin, transitions state, and is part of a workflow. It distinguishes from siblings like 'fix_and_resolve' and 'approve_pin' by specifying the before-start 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?

Explicitly says when to call (before starting work, before changes) and provides next step (fix_and_resolve). Lacks explicit when-not-to-use or alternatives beyond the workflow.

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 full burden. It discloses license scoping and default pin_count, but lacks details on error conditions (e.g., invalid id, already completed) or side effects. Adequate for a simple update but could be more thorough.

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 efficient sentences with no fluff. Purpose, prerequisite, and a key constraint are front-loaded. Every sentence 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 simple two-parameter tool with no output schema, the description covers purpose, prerequisite, and scoping. Missing details on idempotency or status preconditions, but overall complete enough within the broader toolset context.

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

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

Schema coverage is 100% with clear descriptions. The description adds minimal extra value by tying id to get_pending_critiques and explaining pin_count's purpose. Per guidelines, baseline 3 applies.

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

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

The description clearly states the tool marks a critique_queue request as completed after the critic subagent runs, using the request ID from get_pending_critiques. It distinguishes itself from siblings like get_pending_critiques and create_critique_pin by focusing on completion.

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 when to use ('after the critic subagent has run') and provides a critical scoping constraint (cannot complete another tenant's request). Does not list alternative tools for other actions, but the context is clear.

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

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

No annotations provided, so description carries burden. It mentions test message and storage behavior but lacks details on mutation side effects, permissions, or error handling.

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 concise sentences, front-loaded with purpose, 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?

With 9 parameters and no output schema, the description covers defaults and some parameters but doesn't describe return value, error conditions, or success confirmation.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining 'Figma-style subscriptions' and that webhookUrl is stored and not returned, enhancing semantic understanding.

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 'Connect' and the resources 'Pincushion project to Slack or Microsoft Teams using an incoming webhook.' It defines default behavior and distinguishes from sibling tools like list and remove.

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?

Description explains the low-noise defaults and opt-in events, guiding when to use. It doesn't explicitly mention alternatives or when not to use, but the context is clear.

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

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

With no annotations provided, the description fully covers behavioral traits: it mutates state (upserts project row, syncs to cloud, creates deploy hook, inserts bot member), lists traceability knobs (commitTrailers, attributionComments, recordCommitSha), and mentions idempotent insertion. No contradictions.

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

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

The description is a single paragraph front-loaded with the main action and benefit, then details and usage note. Every sentence adds value; no wasted words. Efficiently structured for scanning.

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 12 parameters, no output schema, and high complexity, the description covers purpose, mutation behavior, and usage guidance. However, it does not specify the return value or error conditions (e.g., plan restrictions for commentAccess), which 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?

Schema coverage is 100% with each parameter documented. The description adds context beyond the schema, e.g., explaining why both local and live URLs are needed ('so the extension activates in all environments') and summarizing traceability knobs. Slightly above baseline.

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

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

The description clearly states the action: 'Register a Pincushion project and associate it with your app's URLs.' It uses a specific verb (register/configure) and resource (project), distinguishing it from the read-only sibling `get_project_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?

Explicitly notes when NOT to use: 'if you only need to look up brand context, URLs, or other project metadata, call `get_project_context` instead.' Also explains that this tool mutates state, providing clear context for when to choose alternatives.

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 exist, so the description carries full responsibility. It discloses that the pin must be concrete/actionable, forbids certain topics, and requires reading project context. However, it does not explicitly mention the return value or side effects beyond creating a pin, which marks a minor gap.

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 succinct (~120 words) yet packed with essential rules. It front-loads the invocation restriction, then provides actionable parameter details and process prerequisites. No superfluous sentences; every part 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?

The description covers usage, parameter constraints, prerequisite context checks, and forbidden content. Without an output schema, it could briefly mention expected return (e.g., the created pin ID), but the overall completeness is high given the tool complexity.

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

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

All 8 parameters have schema descriptions (100% coverage), but the description adds significant value: it gives concrete examples ('body <40 words'), clarifies automatic tag addition, specifies selector specificity, and explains severity thresholds. This enriches the schema and helps the agent craft correct calls.

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 creates a pin authored by Pincushion AI and distinguishes it from user-driven actions. It specifies the verb ('Create'), the resource ('pin'), and the context ('AI-driven UI/copy/a11y feedback'), making it unambiguous among sibling tools like approve_pin or claim_pin.

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?

Explicit guidance is provided: 'ONLY call this from the pincushion-critic subagent or the /critique-latest-deploy flow — never from a regular user prompt.' It further states constraints like 'max 3 per page' and prerequisites like checking 'ai.critique.staleness', leaving no ambiguity about when to invoke.

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 full burden. It discloses redemption flow, role restrictions, seat consumption, and return values. Missing details on link revocation or error handling.

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?

Four sentences, front-loaded with the action. Every sentence provides unique value 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?

Covers core behavior, return values, and authorization. Lacks mention of prerequisites (e.g., project membership) or error conditions, but sufficient for typical use.

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

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

All 4 parameters are described in schema (100% coverage). Description adds value by explaining role permissions, default values, and the meaning of maxUses=0, supplementing schema info.

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 generates a Figma-style shareable invite URL for a project, specifying verb and resource. It distinguishes itself from sibling tools like add_member by focusing on link generation rather than direct addition.

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?

Provides authorization context (owners vs editors) and cost implications (Editor links consume paid seats). However, lacks explicit comparison to alternatives like add_member for direct user addition.

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 clearly explains that the link is public, read-only, requires no account, links never expire unless expiresInDays is set, and viewers see live pin status. This fully discloses behavioral traits.

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

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

The description is concise and well-structured: first sentence states the primary action and result, followed by details on accessibility, use cases, optional parameters, and behavior. Every sentence adds information without redundancy.

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

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

Given no output schema and no annotations, the description thoroughly covers what the tool does, what the link contains, sharing properties, optional parameters, and link expiration behavior. It is complete enough for an agent to understand when and how to invoke it.

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

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

Schema coverage is 100% with descriptions for each parameter. The description adds value by explaining defaults (e.g., title defaults to '<N> design notes on <domain>'), constraints (expiresInDays range 1–365), and usage context for each parameter beyond their schema descriptions.

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

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

The description clearly states the tool mints a public read-only crit report link for a project, with specific details on what it contains (numbered pins, threads, screenshots, status, trail). This purpose is distinct from sibling tools like add_agent_reply, approve_pin, etc.

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

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

The description provides usage context: 'Perfect for handing a design crit to a founder/client, or showing stakeholders what shipped.' It also mentions optional scoping to a single page URL. However, it does not explicitly state when not to use this tool vs alternatives.

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 full burden. It explains the generation of the URL, the pre-binding to a project, and contrasts with the public URL behavior. It does not mention response format or side effects, but covers key behavioral aspects.

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 paragraph that is relatively concise (4-5 sentences), front-loading the main purpose and usage guidelines. It could be slightly more structured, but it is efficient and avoids wordiness.

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 5 parameters (1 required), 100% schema coverage, and no output schema, the description adequately explains the tool's context and when to use it. It lacks detail on the response, but the core context for selection and invocation is covered.

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 baseline is 3. The description does not add extra meaning to individual parameters beyond what the schema already provides, but it contextualizes the overall purpose. No additional parameter insights are given.

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 generates an Add-to-Slack OAuth URL pre-bound to a project, with specific verb and resource. It distinguishes from the public storefront URL, which is also mentioned, making 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 explicitly advises that most users should prefer the public storefront URL and to use this tool only for attaching to a specific project. This provides clear when-to-use and when-not-to-use guidance, naming an alternative.

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 key behaviors: transitions to 'resolved' status, disappears from stakeholder view, no thread comment added, and commit linking. No annotations provided, so description carries full burden; it covers major effects but omits potential side effects or reversibility.

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?

Highly concise: three sentences packed with purpose, behavior, and parameter derivation instructions. No wasted words, front-loaded with 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 7 parameters and no output schema, the description adequately covers purpose, behavior, and parameter usage. Lacks return value details, but tool likely returns a success/error status implicitly.

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

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

Schema coverage is 100% (baseline 3). Description adds meaningful context for commitSha, branchName, prUrl (e.g., shell commands to derive values). For other params, it restates schema descriptions but adds linking behavior 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 'resolve' and the resource 'a pin after applying a code fix'. It differentiates from siblings like 'resolve_annotation' by emphasizing the post-fix scenario and the lack of a thread comment.

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?

Provides explicit context on when to use (after a code fix) and instructions for populating commitSha, branchName, prUrl. However, it does not explicitly state when not to use or compare to alternatives like 'resolve_annotation'.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the three categories of pins returned but does not mention potential behaviors like pagination, sorting, performance implications, or whether the operation is read-only (though implied by 'get'). The description is adequate but not exhaustive.

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 plus a bulleted list, highly concise and front-loaded. Every sentence earns its place: the first states the overall purpose, the list details the categories, and the final sentence gives usage guidance. No redundant or filler content.

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

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

Given the tool's simplicity (three optional parameters, no output schema), the description covers the key aspects: what it returns, the three categories, and usage context. It might be missing information on ordering or default limit, but for basic usage it is complete enough.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining the semantics of the 'mode' parameter through the three categories and their meanings (e.g., 'auto-agent' corresponds to pins sent via Send to Agent or YOLO mode). This goes beyond the enum labels in the schema.

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

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

The description explicitly states the tool's purpose ('Get all pins waiting for developer attention') and distinguishes three clear categories that align with the 'mode' parameter. It also positions the tool as the starting point for both auto-agent and manual workflows, clearly differentiating it from sibling tools like get_pending_critiques or get_selected_pins.

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 clear context for when to use this tool ('starting point for both auto-agent workflows and manual review sessions'), implying it is the primary entry point for actionable pins. However, it does not explicitly state when not to use it or mention specific alternatives among sibling tools, which would make it a 5.

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 must convey behavior. It indicates a read operation ('retrieve' and 'understand'), but does not elaborate on side effects, authorization, or data freshness. The description is clear but not rich.

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, front-loaded with the core action, and succinctly provides purpose and usage guidance. No extraneous content.

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

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

Given no output schema, the description does not specify return format, pagination, or ordering. It is adequate for basic understanding but lacks details about what the response contains, which is important for a retrieval 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 description coverage is 100%, so the parameters are already described. The tool description merely restates the filter options without adding new semantic context or examples 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 retrieves annotation pins from the .feedback/ directory with filtering options (page URL, LWC component name, or status). It distinguishes itself from siblings like search_annotations by specifying the directory and filter types, but does not explicitly differentiate usage from other read 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 says 'Use this to understand what feedback exists before making changes,' providing a usage context. However, it lacks explicit when-not-to-use guidance or alternative tools, leaving the choice to the agent.

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 provides clear behavioral context: it retrieves feedback pins and returns element selectors, comments, and thread history. It does not mention destructive or mutating actions, which aligns with the tool's name. Minor gap: no disclosure of whether resolved pins are included.

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 that efficiently convey purpose, benefit, and return contents. No filler or redundancy.

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

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

For a single-parameter tool with no output schema, the description explains the return value reasonably well. However, it could be more precise about the return structure (e.g., list of pin objects) and mention any default filters like status.

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

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

Schema coverage is 100% with a clear description for componentName. The tool description reinforces that the parameter is the target component but adds no new semantic detail beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool retrieves feedback pins for a specific LWC component, with a plain-language summary. It distinguishes from siblings like get_actionable_pins and get_feedback_summary by specifying the component focus and the inclusion of a summary.

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 such as get_actionable_pins or get_feedback_summary. The description implies it is for component-specific feedback but omits selection criteria or prerequisites.

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

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

No annotations provided, so description carries full burden. Clearly states it's a read operation ('Get') providing a rollup. Does not mention rate limits or data freshness, but the behavior is simple and non-destructive.

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 defines what the tool does, second gives usage advice. No redundancy or filler.

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 zero parameters and no output schema, the description sufficiently conveys the tool's purpose and result. Minor gap: doesn't specify if the summary is paginated or sorted, but acceptable for a high-level rollup.

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 defined; schema coverage is 100% by default. The description adds value by explaining that the result includes counts by status, page, and component, providing context 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?

Clear verb 'Get' and resource 'feedback summary', specifies rollup of open feedback with counts by status, page, component. Distinct from siblings like get_component_feedback which focuses on individual component feedback.

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 says 'Use this to plan what to address first', providing a usage context. Does not list when not to use it or alternative tools, but the purpose is straightforward.

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 must disclose behavior. It explains matching (exact or substring) and return shape, but does not mention that the operation is read-only, any required permissions, or potential side effects. For a getter, this is adequate but leaves 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 contains four sentences, each with distinct value: purpose, usage context, return shape, and matching logic. It is front-loaded, no redundancy, and keeps the definition tight.

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

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

Given no output schema, the description details the return structure via cross-reference, helping the agent understand output. Parameters are fully covered. Missing details on error handling (e.g., no match) and potential multiple matches, but overall sufficient for a simple retrieval tool.

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

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

Schema coverage is 100% with both parameters described. The description repeats the matching behavior for 'pageUrl' already in the schema, adding no new semantic meaning beyond aligning with the purpose. Baseline 3 applies.

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

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

The description clearly states it retrieves a single implementation packet for one page URL, specifying the return shape and matching behavior. However, it does not explicitly differentiate from sibling tools like 'get_actionable_pins' or 'implement_approved_pins', relying on implicit 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?

The description notes it is 'useful when you want to batch-fix one page at a time,' which provides usage context. But it does not specify when to avoid using it (e.g., for multiple packets) or name alternatives explicitly.

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 fully covers behavioral traits: return fields (id, page URLs, deploy hash), ordering (newest-first), and pricing/licensing (free, but gating at enqueue). This is comprehensive for a list 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?

Three concise sentences: purpose, return fields, ordering/pricing. No fluff, front-loaded with key information. Every sentence serves a 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?

For a simple list tool with one optional parameter and no output schema, the description provides sufficient context: return fields, ordering, and licensing. Nothing essential is missing.

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, projectId, is already well-described in the input schema (optional filter). The description adds no additional parameter semantics beyond what the schema provides. Schema coverage is 100%, so baseline 3 is appropriate.

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

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

The description clearly states it lists pending critique requests, specifies the source (deploy-hook), and the context of the current license. Verb 'lists' and resource 'pending critique requests' are precise. It distinguishes itself from sibling tools like 'complete_critique_request' by focusing on pending items.

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 via '/critique-latest-deploy' and notes pricing implications, but does not explicitly contrast with alternative tools like 'complete_critique_request' or 'create_critique_pin'. No when-not-to-use guidance is provided.

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

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

Clearly states 'never mutates, never touches the network' and that it is a read-only lookup. No annotations provided, so the description fully discloses 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 well-structured and front-loaded, but slightly verbose with multiple sentences. However, every sentence adds value, so it remains effective.

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

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

Despite no output schema, the description lists the returned fields. It covers all three parameter scenarios (projectId, name, none) and gives context on why this tool is preferred over alternatives. Complete for a simple read 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?

The description adds meaning beyond the schema by explaining how to use projectId for exact lookup, name for display name lookup, and no arguments to list all projects. Schema coverage is 100%, but description enhances utility.

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 is for read-only lookup of a project's context, listing specific fields (name, URLs, brand context, etc.). It distinguishes from sibling tools like configure_project which mutates.

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 says 'Use this whenever you only need to inspect' and contrasts with configure_project. Provides specific advice for the Pincushion AI critic subagent and explains parameter usage for different lookup 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?

With no annotations, the description fully discloses behavior: trigger conditions, idempotency (skip bot-authored latest message), filtering (resolved/archived), and ordering (newest-first). This is comprehensive.

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 front-loaded with purpose, then explains triggers, exclusions, and ordering in a logical flow. It is efficient but the second sentence could be slightly more concise. Overall good structure.

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 only one optional parameter, no output schema, and no nested objects, the description covers all necessary aspects: purpose, trigger conditions, filtering criteria, and ordering. It is complete for the tool's complexity.

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

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

Schema coverage is 100% for the single parameter 'projectId', and the description adds no extra semantics beyond what the schema provides. Baseline of 3 is appropriate.

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

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

The description clearly states the tool returns pins where Pincushion AI should respond, tagged by trigger reason ('mention' or 'reply-on-bot-pin'). It distinguishes from sibling tools by specifying its use case for the slash command and the inclusion of trigger tags.

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 says 'Used by /pincushion-replies' and details triggers and exclusions (skips resolved/archived, bot-authored). It provides clear context for when to use, though it does not explicitly state when not to use or name alternatives.

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 must fully disclose behavioral traits. It describes the return value but does not mention side effects, permissions, rate limits, or whether the operation is safe/idempotent. This is insufficient for an unannotated 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?

Three concise sentences with no redundancy: first defines the tool, second describes output, third provides usage guidance. Each 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 tool with zero parameters and no output schema, the description is largely complete: source (dashboard/PINS.md), return type (IDs with context), and purpose (know what to work on next). Minor gaps exist (e.g., state requirements, availability), but overall adequate.

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

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

There are no parameters, so schema coverage is 100% trivially. The description adds no parameter info because none exist, meeting the baseline of 4.

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 specifies the verb 'Get', the resource 'pins that the developer has selected for implementation', and the scope 'from the dashboard or PINS.md checkboxes'. It distinguishes from siblings like 'get_actionable_pins' by emphasizing 'selected' vs. 'actionable', making 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 last sentence explicitly tells the agent when to use this tool: 'Use this to know which pins the developer wants you to work on next.' It provides clear context but does not mention when not to use it or alternatives.

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 burden. It clearly indicates a read-only operation ('Get instructions') with no side effects. While it doesn't detail return format or data size, the simplicity of the tool makes this acceptable.

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 well-structured sentences, front-loaded with the main purpose, and each sentence adds value (purpose + examples). 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?

Given no output schema, the description sufficiently explains what the tool returns (instructions with configuration examples). It is complete for a simple information retrieval 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?

No parameters exist, so baseline 4 applies. The description does not need to add parameter info.

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

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

The description clearly states the tool retrieves setup instructions for a specific extension, using a clear verb-resource pair. It distinguishes from sibling tools, none of which are about setup.

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

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

The description implies the tool is for obtaining setup instructions and lists example use contexts (various agents). It lacks explicit when-not or alternatives, but given no competing setup tools, it's adequate.

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 that the tool returns a sample size and threshold flag, and explains that the threshold allows callers to hide the metric when the dataset is too small (<5 resolved pins). This provides valuable behavioral context beyond the parameter 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?

The description is two sentences, but the second sentence is somewhat promotional ('This is the marketing proof point...') and does not add functional information. While not verbose, it could be more concise by removing the marketing 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?

There is no output schema, so the description should explain the return value structure. It mentions 'sample size and threshold flag' but does not provide details on the exact format or names of fields. For a metrics tool, this leaves some ambiguity for 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?

Schema description coverage is 100%, so the baseline is 3. The description adds value by explaining the scope parameter in more detail: 'global' is used for the landing widget for aggregate proof, and projectId is required when scope='project'. This goes beyond the schema descriptions.

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

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

The description clearly states the tool computes median and p25/p75 time-to-fix from resolved pins, and returns sample size and a threshold flag. This is a specific verb+resource combination with no sibling tools performing a similar function, so it is well-differentiated.

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

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

The description implies the tool is used for marketing proof points and distinguishes Pincushion. It does not explicitly state when to use versus alternatives, but given the uniqueness of the tool and no similar sibling tools, the usage context is clear enough.

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 full burden. It describes the output structure and usage workflow. It does not mention side effects, auth, or rate limits, but as a retrieval tool this is adequate.

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 four sentences, front-loading purpose. Some redundancy in explaining workflow, but concise overall and well-structured.

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, description explains output shape (packets with CSS selectors, threads, branch name) and how to use it. Missing error cases or detailed return format, but sufficient for this tool.

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

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

Schema coverage is 100% with one optional parameter (projectId). Description adds minimal meaning beyond schema; it repeats the filtering behavior but does not enrich parameter semantics significantly.

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 stakeholder-approved pins grouped into implementation packets, specifying verb 'returns' and resource 'approved pins'. It distinguishes from sibling tools like get_implementation_packet and claim_pin by indicating it is the first step.

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 says 'CALL THIS FIRST when approved pins exist' and provides a workflow: implement_approved_pins → claim_pin → code change → fix_and_resolve. This guides when to use it vs alternatives.

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 for behavioral disclosure. It reveals the overwrite behavior on re-runs, which is a key trait, but does not cover authentication requirements, error states (e.g., invalid annotationId), or the extent of side effects beyond the dashboard display.

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 three sentences long, front-loaded with the core action. Every sentence contributes essential information without redundancy.

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

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

Given the lack of output schema and three parameters, the description adequately covers the tool's purpose, typical invocation context, and idempotency behavior. It lacks details on error handling or return values, but the tool's simplicity makes this acceptable.

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?

All three parameters have descriptions in the schema (100% coverage), so the description adds limited extra meaning. It provides context ('Typically called by the deploy-hook...') but does not enrich the parameter semantics beyond what the schema already 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 opens with 'Link a deploy URL to a resolved pin', which is a specific verb+resource combination. It clearly distinguishes this tool from its many siblings by focusing on a unique linking 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 explicitly states it is 'Typically called by the deploy-hook edge function once a deploy that includes the pin's fix goes live', providing clear usage context. It also notes that re-runs overwrite previous URLs, implying idempotent behavior, but doesn't mention when not to use it or alternatives.

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

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

The description mentions that webhook URLs are masked, which is a helpful behavioral detail. However, it does not disclose other traits such as read-only nature, authentication requirements, or rate limits, which are important since no annotations are provided.

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 sentences, no unnecessary words, and effectively front-loads the purpose.

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

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

Given the lack of an output schema, the description gives a basic idea of what is returned (subscriptions with masked URLs) but does not mention other fields like subscription names or statuses, leaving some ambiguity.

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

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

Schema coverage is 100% and the schema already describes the only parameter (projectId). The description does not add any additional meaning 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 verb 'List' and the specific resource 'Slack and Microsoft Teams webhook subscriptions for a Pincushion project', which distinguishes it from sibling tools like configure or remove.

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 context for when to use the tool (for a Pincushion project) but does not explicitly state when to use it versus alternatives like configure_collaboration_integration or remove_collaboration_integration.

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 conveys a read-only listing operation but omits details like pagination, permissions, or return format. For a simple list tool, this is minimally adequate but not fully 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, front-loaded sentence with zero wasted words. It efficiently conveys the tool's primary action and additional output detail.

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 low complexity (1 parameter, no output schema), the description is largely complete for a list operation. However, it lacks mention of pagination or limits, and the return shape is unspecified, leaving minor gaps.

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

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

Schema coverage is 100% with one parameter (projectId) that already has a clear description. The tool description does not add additional parameter semantics beyond what the schema provides, matching the baseline for high 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 verb 'List' and the resource 'members of a PinCushion project', with additional detail about including roles and seat usage. It effectively distinguishes itself from sibling tools like add_member and remove_member.

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

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

The description implies usage for viewing membership, but does not explicitly state when to use versus alternatives or provide exclusions. The context from sibling names helps, but no direct guidance is given.

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

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

No annotations are provided, so the description carries the full burden. It states the tool is a preview, implying non-destructive behavior, but does not detail the output, auth needs, or side effects. It adds value beyond the schema by explaining the preparatory context, but could be more explicit.

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 is concise and front-loaded. It includes the essential information without any waste, earning its place efficiently.

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

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

Given the tool's simplicity (2 params, no output schema, no annotations), the description is sufficient. It explains the use case and timing. It does not cover return format, but that is less critical for a preview tool. Overall, it is complete enough for an agent to understand.

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

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

Schema description coverage is 100%, so the schema already documents both parameters with enums and descriptions. The tool description does not add new meaning to the parameters, just restates them indirectly (Slack/Teams, events). Baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: to preview the notification shape and routing for Slack/Teams before connecting a webhook. It uses a specific verb 'preview' and identifies the resource (notification shape/routing), distinguishing it from sibling tools like configure or list integrations.

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 clear context on when to use this tool: 'before connecting a real webhook.' It implies a preparatory step, but does not explicitly state when not to use it or mention alternatives. This is good but leaves some room for interpretation.

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 conveys that this is a write operation recording a verification outcome and displays the verdict on the dashboard. It does not describe idempotency, side effects, or error behavior, but it adequately covers the core behavior for a simple recording 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?

Three sentences with no fluff. First sentence states purpose, second specifies caller, third explains impact. Efficient and well-structured.

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 all described in schema and no output schema, the description provides sufficient context about when and why to use the tool. It covers the caller, purpose, and result. It could briefly mention how notes are displayed or the meaning of 'pending', but overall complete for the use case.

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

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

Schema coverage is 100%, so baseline is 3. The description mentions the status values like 'verified', 'regressed', 'inconclusive', but these are already defined in the schema with enum descriptions. The description adds no additional meaning 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 verb 'Record the outcome' and the resource 'on a resolved pin', specifying it is for post-deploy verification by a critic subagent. It distinguishes from sibling tools like 'approve_pin' or 'resolve_annotation' by focusing on the AI verification use case.

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 it is called by the critic subagent after auto-critique on a fresh deploy, providing clear context when to use. However, it does not list explicit exclusions or alternatives, though the context implies it is not for general pin updates.

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 should fully disclose behavioral traits. It confirms the removal action but fails to mention if it is irreversible, requires specific permissions, or affects other services.

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 is concise and front-loaded. It is appropriate for a simple removal tool, though it could provide 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 lack of annotations and output schema, the description is insufficient. It does not explain the interplay between provider and integrationId, default behavior, or potential consequences of removal.

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

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

Schema coverage is 100%, so the schema fully describes parameters. The description adds no additional context about parameter usage or relationships beyond what is in the schema.

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

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

The description clearly states the verb 'Remove', the resource 'webhook subscription', and the scope 'from a Pincushion project'. It specifies the providers (Slack or Microsoft Teams), effectively differentiating from sibling tools like configure_collaboration_integration or list_collaboration_integrations.

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. It does not mention prerequisites, such as obtaining an integration ID from list_collaboration_integrations, nor does it suggest 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 provided, the description carries the burden. It discloses seat freeing for editors, which is helpful, but lacks details on reversibility, notifications, or impact on shared work. The description adds some behavioral context but remains minimal.

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, front-loaded, and every word adds value. No redundancy or unnecessary 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 simple nature of a removal tool with two parameters and no output schema, the description adequately explains the core action and a key side effect. It is mostly complete, though additional details on side effects or system behavior could improve it.

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

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

Schema coverage is 100%, and the description adds no extra meaning beyond what the schema already provides for email and projectId. Baseline 3 is appropriate as the description does not enhance parameter understanding.

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 removes a collaborator from a PinCushion project and specifies a key side effect (freeing a seat for editors). This distinguishes it from siblings like add_member and remove_collaboration_integration.

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 removing collaborators but provides no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives or prerequisites, offering only implied context.

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

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

No annotations provided, yet description fails to disclose behavioral traits like irreversibility, permissions required, or notifications triggered. Only states the action without additional 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?

Single sentence, front-loaded with the action, no redundant 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?

Covers main action and optional comment, but lacks behavioral details and fails to leverage sibling context for completeness. Adequate for a simple tool but not exemplary.

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

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

Schema coverage is 100%, so baseline is 3. Description adds minimal context (comment explains change), but does not significantly enhance understanding over schema defaults.

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 'Mark' and resource 'annotation as resolved', clearly distinguishing from siblings like 'fix_and_resolve' which combines fixing and resolving, and 'search_annotations' which is read-only.

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?

Implies usage 'after addressing the feedback' but does not explicitly compare with alternatives such as 'fix_and_resolve', nor states when not to use this tool.

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, description carries full burden. It lists searchable fields but omits behavioral details like performance, pagination, auth needs, or search syntax. Adequate but minimal.

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 with no wasted words, key info 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?

Fairly complete for a simple search tool with one parameter, but lacks return format, pagination info, or limitations.

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

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

Schema coverage is 100%, so baseline is 3. Description adds no extra meaning beyond schema's 'Search query string'.

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 performs full-text search across specific annotation fields (comments, selectors, component names, tags), distinguishing it from sibling tools like get_annotations.

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 vs alternatives (e.g., get_annotations). Usage is implied but not contrasted with sibling 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?

No annotations provided, so description bears full burden. It discloses that the tool resolves user across all Slack workspaces, but does not mention permissions, idempotency, or side effects beyond the described behavior. Adequate but could be more explicit.

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

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

Well-structured with clear first sentence, then resolution process, then examples. Slightly long but each sentence adds value; no waste.

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

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

Handles all parameters with schema descriptions, but no output schema and description does not detail return structure (only mentions 'see current state'). For a tool with 11 parameters, this is a gap in completeness.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining the intent behind parameters (e.g., 'mute is a friendly alias', 'digestMode reserved for future'), enhancing understanding beyond the schema.

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

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

The description clearly states 'Read or update the caller's Slack DM preferences', providing a specific verb-resource pair. It distinguishes from sibling tools which focus on pins, replies, and critiques, making this unique.

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?

Provides clear usage examples (with no args, with mute, with event flags) and context ('useful for mute pin DMs during this refactor workflows'). Does not explicitly state when not to use, but covers main use cases.

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 that this is a write-only operation, does not create deploy hooks or sync members, simply persists and pushes to cloud. It explains the roles of critiqueContext, critiqueSignals, and critiquePolicy. However, it does not cover failure modes or idempotency.

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 paragraph, efficiently front-loaded with the core purpose and usage context. Every sentence adds value, but there is minor redundancy in explaining the role of each field both in description and schema. Slightly verbose but still clear.

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 (5 parameters, nested object, no output schema), the description covers the tool's purpose, usage context, and parameter semantics adequately. It lacks details on return values or error scenarios, but the absence of an output schema reduces the burden. Slightly incomplete on success behavior.

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

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

Despite 100% schema coverage, the description adds significant meaning: critiquePolicy is user-editable and persists across recompiles; critiqueContext is what the AI critic reads; critiqueSignals is raw input not directly read by critic. It also gives a recommended shape for critiqueSignals, adding context beyond schema.

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

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

The description clearly states it is a 'lightweight write-only path for the layered critique-context system' that persists the compiled brief. It explicitly contrasts with the sibling tool `configure_project`, listing what it does not do, making its purpose distinct and specific.

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 says to use this from /setup and /refresh-brand after gathering repo signals, and contrasts with `configure_project` by listing excluded actions (no deploy hook, sync members, validate URLs). This provides clear when-to-use and 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?

Without annotations, description covers auth requirements (owner/editor only), destructive behavior (re-upload replaces), image constraints (≤5MB, JPEG/WebP), and pageUrl matching requirement. Missing rate limits but 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?

Single paragraph efficiently covers all key points without fluff. Front-loaded with purpose. Could be slightly more structured but remains 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?

Given 8 parameters (4 required) and no output schema, description provides comprehensive workflow, parameter usage, and constraints. Lacks return value details but tool is action-oriented.

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

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

Schema coverage is 100% but description adds significant context: explains imageB64 vs imagePath preference, pinPositions coordinate meaning, contentType defaults to JPEG, and that omitted pins render in notes list. Adds value beyond schema.

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

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

Description clearly states verb 'Upload a full-page screenshot' and specific resource 'turn public share report into an annotated page'. It distinguishes from siblings by being the only tool handling snapshot upload with pin mapping.

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?

Provides explicit preparation steps (kill animations, scroll, etc.) and permissions ('Owner/editor only'). Does not contrast with alternatives but context implies uniqueness.

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