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

No annotations are provided, so description carries full burden. It describes the output format (JSON array of 5 recommended skills with fields) and the ranking by relevance. It does not mention side effects, but the tool is clearly read-only analysis. Could mention that it does not install anything.

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 plus a usage note. Every sentence adds value: what it does, output format, when to use, when not to use. No unnecessary words.

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

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

For a tool with 3 required params, no output schema, and no annotations, the description is complete enough. It explains the output structure and usage boundaries. Could mention if there are side effects or rate limits, but not essential given the tool's nature.

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% (all parameters have descriptions). Description adds value by providing concrete examples for task and current_tools, and explaining the agent_type enum. This helps the agent format inputs correctly.

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 states it analyzes tasks agent cannot complete and suggests skills to fill the gap. Clearly distinguishes from siblings like search_skills (when you know what skill you need) and list_categories (general browsing).

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 when you encounter a task requiring capabilities you lack, and provides clear exclusions: do not use for general browsing (use list_categories) or when you already know what skill you need (use search_skills).

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 return format and status values but does not mention potential error responses or side effects. Adequate for a simple read-only check, but could add more behavioral 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, informative sentences with no wasted words. Important information (purpose, usage, constraint) is presented 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?

Covers purpose, usage context, return format, and a constraint. Lacks error handling details but is largely complete for a polling tool without an output schema.

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

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

Schema already describes the request_id parameter fully. The description reiterates the need for a valid request_id but does not add new semantic details beyond the schema. Baseline 3 due to 100% schema coverage.

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

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

Clearly states the tool checks status of a permission request and returns a JSON object with specific status values. Distinguishes itself from siblings like request_permission by focusing on checking results.

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 to use after request_permission and to poll for decisions. Also states a negative condition: do not call without a valid request_id, which provides clear when-not guidance.

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

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

With no annotations provided, the description carries full burden. It discloses that flags are reviewed by moderators and may lead to removal or downgrading, and that a confirmation is returned. While it doesn't mention rate limits or irreversibility, the key behavioral aspects are covered.

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

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

The description is four sentences that front-load the core action and return value, then progressively add usage guidance and outcome detail. Every sentence serves a distinct purpose without redundancy, achieving maximum 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 low complexity and full schema coverage, the description sufficiently covers purpose, usage, and behavior. It lacks explicit mention of potential side effects like duplicate flags or rate limits, but for a simple reporting tool, the provided information is adequate for correct invocation.

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

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

The input schema has 100% description coverage with clear meanings for slug, reason (enum), and details. The description adds minimal extra value beyond stating it returns a confirmation. It does not explicitly note that 'details' is optional, though the schema implies it. Baseline 3 is appropriate given high schema coverage.

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

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

The description clearly states the action 'report a problematic skill' and specifies the resource (skill) and destination (moderation team). It distinguishes from siblings like 'review_skill' by listing specific problematic categories (prompt injection, malicious, etc.), making the tool's purpose unmistakable.

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 provides when to use the tool (encountering specified issues) and when not to (skills that simply don't meet needs, directing to leave a review instead). This clear differentiation from 'review_skill' offers excellent guidance for the AI 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?

Describes what the returned JSON contains (name, description, type, quality_score, stars, security_score, safety manifest, install configs for 12 platforms, usage hints). Missing mention of read-only nature, error handling for non-existent slugs, or rate limits, but covers main behavioral aspects adequately.

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

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

Two sentences, front-loaded with main action, then structured list of returned fields, then usage guidance. 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?

With no output schema, the description compensates by listing all returned fields. Missing note on error handling for missing slug. Covers usage, param, and return value well.

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?

Parameter 'slug' has 100% schema coverage with description and examples. The description adds extra context: slug format (owner/repo), examples, and advice to use search_skills if slug unknown.

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 gets comprehensive details for a specific skill by slug. Distinguishes from sibling tools by explicitly stating not to use for discovery (use search_skills or recommend_skills instead).

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 (when you know exact slug and need full metadata before installing) and when not to use (for discovery), with clear alternatives (search_skills, recommend_skills).

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 the full burden. It discloses the JSON response structure with results and not_found arrays and imposes a 20-skill limit. However, it does not mention whether installation is idempotent or overwrites existing configs.

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, followed by return info and usage guidance. No unnecessary words or repetition.

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 2 parameters, 100% schema coverage, no output schema, the description fully covers purpose, response format, constraints, and alternatives. Agent has sufficient information to decide and invoke correctly.

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

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

Input schema already has 100% coverage with clear descriptions for both parameters (slugs, agent). The description restates the 20-skill limit but adds no additional semantic value beyond what the schema provides.

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

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

Clearly states 'Install multiple specific skills in a single call.' Distinguishes from siblings like install_pack (curated collections) and install_skill (single skill) by explicitly naming the alternative usage.

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 when-to-use ('when you need to install 2-20 specific skills at once and you know all their slugs') and when-not-to-use ('Do not use this for curated collections – use install_pack instead'). Also states maximum of 20 skills.

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?

Describes the return format (formatted text with skill details) and mentions packs are pre-built collections. With no annotations, this is sufficient behavioral disclosure for a non-destructive install action.

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 well-structured sentences: purpose, return format, usage guidance. No filler or repetition. Front-loaded with 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 all necessary aspects for a simple installation tool: what it does, what it returns, when to use it, parameter examples. No output schema needed.

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

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

Both parameters are already described in schema (100% coverage). The description adds value by explaining the concept of packs and providing examples for the slug parameter, making the agent better informed.

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 installs all skills from a curated pack in one call, and distinguishes from individual installation. Provides concrete examples of packs and their contents.

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 this tool (setting up for a specific role) and when not to (only need one skill), including the alternative tool name (install_skill).

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. States the tool is read-only ('does NOT write any files') and mentions memory side effect. Could add more on required permissions or error conditions, but adequately describes core behaviors.

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 purpose and return format. Some redundancy (e.g., 'This tool is read-only' repeated from context). Could be tightened but overall efficient.

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

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

No output schema, so description compensates by detailing return object fields. Covers side effects (memory save) and limitations. Missing error handling or prerequisites (e.g., authentication), but acceptable given tool simplicity.

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

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

Schema coverage is 100% with descriptions. Description adds context about return format (config_path, config, instructions) and confirms slug format (owner/repo). Also provides insight into how agent enum values map to platforms (e.g., 'claude-code' for .claude/settings.json), adding 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?

Clearly states 'Get the platform-specific configuration JSON needed to install a single skill', with a specific verb (get/config) and resource (config JSON for a skill). Distinguishes from siblings by mentioning batch installs and packs.

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 when the user wants to install a specific skill...' and warns 'Do not use this for batch installs (use install_batch instead) or for packs (use install_pack instead)'. Also notes that the skill slug is automatically saved to agent memory.

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 transparently describes the return format (JSON array with slug, name, description, skill_count, tags) and lists all categories. No hidden side effects or behaviors.

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 waste. Front-loaded with the action and resource. Every sentence adds value: what it does, the return format, and usage guidance.

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 zero-parameter tool with no output schema, the description is complete. It explains the purpose, return structure, and specific content (categories). No gaps.

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

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

Input schema has 0 parameters with 100% description coverage. The description adds value by detailing return fields, which compensates for the lack of parameter info. Baseline is 4 due to zero parameters.

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

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

The description clearly states 'List all 10 skill categories' with a specific verb and resource. It lists the exact categories and return fields, distinguishing it from sibling tools like search_skills.

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 help the user browse skills by domain when they do not have a specific search query.' Provides clear when-to-use context but does not explicitly name alternatives or when not to use.

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

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

No annotations are provided, so the description must carry the behavioral burden. It accurately describes the tool as read-only (listing proofs), explains the return structure, and states the empty array condition. However, it does not disclose any potential side effects or permission requirements, which are minimal for a list operation.

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 (four sentences) and front-loads the main purpose. It wastes no words, though it could be slightly more structured with bullet points for the fields.

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 (no parameters, no output schema), the description is complete. It explains what the tool returns, provides context ('like an agent resume'), usage scenarios, and a note on when it returns an empty array. No additional information is needed.

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

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

The input schema has zero parameters, and the description explicitly states 'No parameters required.' This is sufficient for a parameterless tool, adding clarity beyond the schema.

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

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

The description clearly states the action ('List all execution proofs') and resource ('created by this agent'). It specifies the output format (JSON array with fields). However, it does not explicitly differentiate from sibling tools like 'verify_proof' or 'report_skill_usage', which could cause confusion.

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 use cases ('review your usage history, share proof links, or verify your trust score') and notes that an empty array is returned if no skills have been reported. However, it does not mention when not to use this tool or suggest alternatives such as 'verify_proof' for verification.

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 depends on itself. It discloses the return format (JSON with memories array), empty array if none, and filtering by type. It does not mention any side effects, but as a read-only retrieval, this is adequate. No contradictions with annotations.

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

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

The description is three sentences long, each providing essential information: purpose, return format, and usage guidance. It is front-loaded and contains no redundant 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 the single optional parameter and the absence of an output schema, the description adequately explains the return structure (memories array with key, value, type) and the behavior when no memories exist. It is complete for the tool's simplicity.

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

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

The only parameter 'type' is fully described in the schema with enum values and a description. The description reiterates the filtering capability but adds no additional meaning beyond the schema. Since schema coverage is 100%, the baseline of 3 is appropriate.

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

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

The description clearly states the verb 'Retrieve' and the resource 'previously saved memories,' making its purpose unambiguous. It distinguishes itself from sibling tools like 'save_memory' by focusing on retrieval and restoration of 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 explicitly advises using this tool at the start of every session to restore context, installed skills, and user preferences, providing clear usage context. However, it does not mention when not to use it or compare it directly with alternative tools.

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

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

With no annotations, the description fully covers behavior: it returns 5 ranked skills with specific fields. It implies a read-only operation ('Get') and no side effects. The description adds clarity about the recommendation logic (context-based, excluding installed skills) beyond what the schema provides.

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 that are front-loaded: first sentence states the primary action and output, second gives usage guidance, third provides exclusions and requirements. No wasted words; 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?

Despite no output schema, the description details the exact output structure. It covers purpose, usage, exclusions, and parameter descriptions. Combined with high schema coverage, the tool is fully specified for correct invocation.

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

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

Schema coverage is 100%, with both parameters well-described. The description reinforces the context parameter's importance and explains the purpose of the installed parameter (to exclude already installed skills). This adds value beyond the schema by linking parameters to usage intent.

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 function: 'Get personalized skill recommendations based on a project description.' It specifies the output format (JSON array of 5 skills) and explicitly distinguishes from the sibling tool search_skills, eliminating ambiguity.

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 when-to-use scenarios ('when starting a new project to discover relevant tools, or when you need capabilities beyond your current toolset') and when-not-to-use ('Do not use this for searching by keyword'), along with a direct alternative (search_skills). Also notes the requirement for a descriptive context string.

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 behavioral traits. It states the proof is permanently recorded and affects quality scores, promoting honesty. But it lacks details on authentication, rate limits, or side effects beyond recording.

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 5 sentences, front-loaded with the core purpose and return value. It includes necessary usage guidance and parameter hints. A bit verbose in the middle sentences but overall efficient.

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

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

Given no output schema, it sufficiently describes the return object and the permanent record. It addresses prerequisites by warning not to call before using the skill. It covers the essential aspects for an agent to use it correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context: slug format, status implications for quality scores, and conditional requirement for error_message. This goes beyond the schema descriptions, justifying a higher score.

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 states the tool reports the outcome of using a skill, generating a verifiable proof. It uses specific verbs and a clear resource. However, it doesn't explicitly differentiate from sibling tools like verify_proof, which might also deal with proofs.

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 to use after every skill invocation and not before using the skill. It also mentions building trust score and helping the community. However, it doesn't describe alternatives or when not to use.

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

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

With no annotations, the description carries the full burden. It reveals the return format (JSON with request_id and status 'pending'), implying it creates a pending request. Additional details like side effects or blocking behavior are absent but not critical.

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 with no wasted words, front-loaded with purpose and return, followed by usage guidelines. 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 permission request tool with two parameters and no output schema, the description covers purpose, return, and usage conditions. Minor gaps like error handling do not significantly reduce 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% and the description adds value by providing an example for the 'reason' parameter, clarifying its intent beyond the schema's description.

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: requesting permission before installing a skill, which is a specific verb+resource. It is distinct from sibling tools like check_permission which checks status.

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 guidance on when to use this tool (security grade C/F, high risk, sensitive permissions) and when not to use (A-graded unless manual approval). This fully informs the agent about appropriate 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 provided, so description must carry the burden. It states the tool returns a 'confirmation that the review was recorded' and explains reviews help others. However, it doesn't disclose whether reviews can be updated or deleted, or if there are any side effects beyond recording. For a straightforward write operation, this is adequate but not exceptional.

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 with clear structure. Front-loaded with purpose, then return value, then usage guideline, then rating range. No unnecessary words, but could be slightly more concise.

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

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

Given no output schema, the description adequately mentions the return type (confirmation). All parameters are explained, and the tool's role in the ecosystem (helping others decide) is noted. Adequate for a review tool with simple parameters.

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 already provides detailed descriptions for all parameters (slug, rating, comment). The description adds context about rating range (1-5) and examples for comment, but does not provide significant additional meaning beyond the schema. With 100% schema coverage, baseline is 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?

The description clearly states the tool's purpose: 'Leave a rating and optional comment for a skill you have used.' It differentiates from sibling tools like get_skill or install_skill by being the only tool for reviewing. The verb 'review' plus resource 'skill' is specific and unambiguous.

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

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

Explicitly states when to use: 'after using a skill to share your experience.' Also advises against reviewing skills not actually used. While no alternative tools are mentioned, the context is clear and sufficient for an AI agent to decide to use this tool after skill use.

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

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

No annotations provided, so description carries full burden. It explains persistence across sessions, return confirmation, and data sensitivity. Missing details on overwrite behavior or error handling, but covers core behaviors well.

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

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

Description is concise, front-loaded with purpose, and every sentence provides value. No redundant or unnecessary text.

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

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

The description adequately explains the tool's purpose, usage, parameters, and return value. Lacks details on edge cases (e.g., duplicate key) but is sufficient for an agent to use effectively.

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

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

Schema coverage is 100% with descriptions for all parameters. The description adds usage examples for key and value, but doesn't significantly enhance meaning 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 action ('Save a key-value pair') and the resource ('persistent agent memory that survives across sessions'). It distinguishes from sibling tools like recall_memory by focusing on storing rather than retrieving.

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 recommends when to use (e.g., remember installed skills, user preferences) and warns against storing sensitive data. Directs to use recall_memory for retrieval, providing clear 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 returned JSON format with fields, implying read-only behavior. However, it does not mention edge cases like empty results, rate limits, or authentication, but these are minor for a search tool.

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

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

The description is mostly concise (two sentences) but the first sentence is dense, combining purpose and output format. It is front-loaded with the main action but could be slightly more 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, the description adequately describes the output with specific fields. It also provides usage guidance and scope. Minor gaps: no mention of error handling or pagination beyond the limit parameter.

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

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

Schema coverage is 100%, and schema descriptions are already detailed. The tool description does not add significant meaning beyond the schema—it mostly restates output format rather than parameter behavior. 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 searches a registry of 20,000+ skills by keyword, and distinguishes itself from siblings by specifying when to use alternative tools (get_skill for known slugs, smart_search for personalized results).

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 advises when to use (broad discovery, unknown slug) and when not to use (known slug → get_skill), and recommends smart_search for personalized results, providing clear decision 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?

Describes return value (confirmation) and notes profile appears on a public page. No annotations provided, so description compensates well by disclosing the update behavior and optional fields.

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 wasted words. Front-loaded with action and resource, then adds necessary context.

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 two optional parameters and no output schema, the description covers purpose, usage, behavior, and parameter details adequately. Mentions return value and public page URL.

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

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

Schema has 100% coverage with descriptions. The description adds value by stating both fields are optional and can be updated independently, enhancing understanding beyond schema.

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

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

Clearly states the tool sets/updates the agent's public profile display name and bio, specifying the exact resource and action. Differentiates from sibling tools that deal with skills, memory, permissions, 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?

Explicitly advises use during initial setup or when customizing public identity. Could be improved by stating when not to use, but the context is clear and no alternatives are needed.

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

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

No annotations provided, but description implies read-only behavior ('Get...public profile') and lists return fields including a shareable URL. It does not mention side effects, auth, or rate limits, but for a simple read tool the transparency 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?

Three sentences: purpose, return details, usage guidance. No redundant words, front-loaded with key information.

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

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

No output schema, but description fully enumerates return fields (agent_key, trust_score, etc.) and explains usage context. For a zero-parameter tool, it is complete.

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

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

No parameters exist, schema coverage is 100%, and description correctly omits parameter details. Baseline 4 is appropriate.

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

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

The description clearly states 'Get this agent's public profile' and enumerates specific fields (trust_score, installed_skills, etc.), making it distinct from sibling tools which focus on installing, checking, or searching skills.

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 use cases: 'display the agent's current capabilities' or 'share your configuration with other agents'. No need for when-not-to-use given simplicity, and no similar sibling exists for profile retrieval.

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 discloses the automatic exclusion of installed skills and application of preferences, and details the return structure (results array fields, total count, personalization metadata). This goes beyond the input schema. However, it doesn't explicitly state it's read-only or mention potential side effects, though for a search tool that is typically safe.

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. It front-loads the purpose and behavior, then provides output details, and ends with usage guidance. Every sentence earns its place without redundancy.

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

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

Given the tool has 2 parameters, no output schema, and no annotations, the description fully compensates by describing the output structure in detail. It covers purpose, behavior, usage guidance, and output format, making it complete for an agent to use correctly. No obvious gaps.

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

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

Schema description coverage is 100%, so the schema already documents both parameters well. The description does not add significant parameter-level detail beyond what the schema provides, but it does provide context about the search behavior. According to guidelines, baseline is 3 when schema coverage is high.

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 personalized skill search that excludes installed skills and applies preferences. It explicitly distinguishes itself from sibling search_skills, specifying when each should be used.

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 explicit guidance: 'This is the preferred search tool for most use cases. Use search_skills only when you need unfiltered results or specific type/agent filters.' This clearly defines when to use this tool vs the 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?

No annotations provided, so description carries full burden. It discloses checks performed and return fields. Missing details like side effects, error handling, or prerequisites, but overall sufficient for a read-only validation 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?

Concise, front-loaded purpose, then methods, then usage instruction. No wasted sentences.

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 annotations, no output schema, and 3 parameters (2 required, nested object), the description is fairly complete. It covers purpose, checks, return fields, and usage. Lacks info on what happens on failure or prerequisites, but 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?

Input schema has 100% coverage with parameter descriptions. Description adds minimal extra context (e.g., 'Pass the exact parameters you intend to use'). Baseline 3 is appropriate as schema already documents parameters well.

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 'pre-flight safety check' before executing an action on a skill, listing what it returns (validation result with fields) and what it checks (security grade, safety manifest, injection patterns, recency). This distinguishes it from siblings like check_permission and check_capability_gap.

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 before calling any skill action that could have side effects' and 'Do not skip this step for skills with security grade C or F,' providing clear when-to-use and when-not-to-skip 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 describes return value structure (JSON with verification status, skill slug, agent, timestamp) and implies no side effects. Lacks explicit mention of error responses or authentication needs, but sufficient for basic transparency.

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

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

Three sentences, all critically informative: purpose+output, use cases, and sibling exclusion. No wasted words, front-loads primary 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 purpose, parameter source, return structure, and usage guidance. Slightly missing error conditions (e.g., invalid proof ID), but given simplicity and absence of output schema, it is adequate for agent decision-making.

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% with format and example. Description adds practical guidance: 'Obtain proof IDs from report_skill_usage responses or list_my_proofs results.' This provides 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?

States clearly: 'Verify the authenticity and validity of an execution proof by its ID.' Provides specific verb (verify) and resource (execution proof), and distinguishes from sibling list_my_proofs by explicitly directing agents away from listing.

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 describes when to use: 'confirm that another agent's claimed skill usage is genuine, or to validate your own proofs before sharing them.' Also states when not to use: 'Do not use this for listing proofs (use list_my_proofs instead).' Provides clear alternative.

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