SkillAgent

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

Beyond the readOnlyHint annotation, the description discloses the exact return content (Markdown with summary, metadata, install command, and skill file) and the URL structure for identifiers. This adds meaningful behavioral context without repeating the annotation.

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

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

The description is two sentences with no filler. The first sentence front-loads the primary purpose and output, and the second sentence provides the parameter derivation rule. Every element is purposeful.

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

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

For a read-only tool with two simple parameters, no output schema, and readOnlyHint annotations, this description covers the essential invocation details: what to pass, how to derive it, and what will be returned. No critical information for an agent to call it correctly 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?

Even though the input schema already describes both parameters with 100% coverage, the description adds a relational mapping (owner and name as last two URL segments), which clarifies how the two parameters connect and how to derive them. This goes beyond the schema's individual 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 states a specific action ('Get one skill') and the resource ('skill') with a precise output format ('as Markdown: summary, metadata, install command and the full skill file'). It also explains the owner/name mapping to pageUrl, which clearly differentiates this from siblings like search_skills or install_skill by specifying a single, identifiable skill.

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 how to construct the owner and name from the skill's pageUrl, which is a practical usage guideline. However, it does not explicitly mention when not to use this tool or point to alternatives like search_skills when the skill slug is unknown, so it lacks explicit exclusion conditions.

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

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

Annotations already declare readOnlyHint=true, and the description reinforces this by stating 'This tool does not install anything'. It adds valuable behavioral context: the refusal condition (isError at 'warning' safety scan), the requirement to get user approval before applying, and the inclusion of a safety summary. The only minor gap is not detailing the exact error shape, but the refusal behavior is clearly disclosed.

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 dense but well-structured: it front-loads the core purpose, then covers the non-installation caveat, the approval requirement, the safety summary, the refusal condition, and parameter derivation—all in three sentences with no 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?

For a read-only informational tool with 100% schema coverage and no output schema, the description is complete. It tells the agent what the tool returns (install command or file content), what to do with that result, when it errors, and how to construct the parameters. Nothing essential is missing 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 description coverage is 100%, so the schema already documents all three parameters. The description adds meaning by explaining that `owner` and `name` are the last two segments of a skill's pageUrl, which is not in the schema. It also clarifies that `agent` is the target installation environment. This goes beyond the schema's basic 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 states a specific verb ('Get installation instructions'), a precise resource ('one skill on one agent'), and the exact output (install command or file to create). It also distinguishes itself from siblings by clarifying it does not install anything, which separates it from get_skill and other skill-related 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 explicitly says when to use it ('Exact installation instructions for one skill on one agent'), what to do after calling it ('apply the result yourself, and only after showing the user the skill and getting their approval'), and when it refuses ('when the skill's safety scan is at warning'). It also explains how to derive the parameters from a skill's pageUrl, which is 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?

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds valuable context: it explicitly states ranking is deterministic (aligning with openWorldHint=false), discloses that skills with safety 'warning' or missing sources are excluded, and that the result reports how many were excluded. This goes beyond the annotation's safety profile and gives the agent concrete expectations about output composition.

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, well-structured paragraph that front-loads the core purpose and input types before explaining output format and ranking behavior. Every sentence carries information—no filler. It is concise yet comprehensive for a tool of this complexity.

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

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

With no output schema, the description fully explains the return shape: a ranked shortlist with each entry containing the skill record and a `why` string that breaks down match reasons (matched terms, agent fit, freshness, quality, safety). It also covers exclusions and the deterministic ranking. For a 6-parameter tool with no output schema, this is unusually complete—an agent knows exactly what to expect.

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 83%, so the schema already documents each parameter with examples. The description adds marginal value by mapping 'languages, frameworks or dependencies' to the input concept and noting that 'skills made for it rank higher' for the agent parameter. This is helpful but does not significantly alter parameter 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 states a specific verb ('recommend') and resource ('skills for a project'), and immediately distinguishes it from siblings like get_skill, install_skill, and search_skills by describing the ranked-shortlist output with a `why` explanation. This is clearly a recommendation tool, not a fetch, install, or generic search tool.

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: when you have a project description (task, agent, languages, etc.) and need a ranked shortlist. However, it does not explicitly state when to use this tool over alternatives like search_skills, nor does it provide exclusions (e.g., 'use search_skills when you need keyword search only'). The context is clear but lacks explicit routing 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?

The annotations already declare readOnlyHint=true and openWorldHint=false, so the read-only nature is covered. The description adds that the tool returns matching skills with several fields, which is useful, but it does not disclose pagination behavior, result ordering, or other operational details beyond the annotation-covered safety profile.

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

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

The description is a single sentence that front-loads the action and scope. The list of return fields adds length but is justified since there is no output schema; still, the enumeration makes it slightly less concise than it could be.

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 optional parameters and no output schema, the description gives a reasonable high-level picture and lists return fields, but it omits guidance on default sorting, pagination, and how to combine filters. It is adequate for a basic search call but not complete for sophisticated use.

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

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

Schema description coverage is only 63%, so the description should partially compensate for undocumented parameters. It does not explain sort, limit, offset, category, platform, or how filtering interacts with the search, and the return-field list only weakly hints at format and freshness as relevant dimensions.

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 a specific verb ('Search') and resource ('SkillAgent catalogue of AI agent skills, rules files and MCP servers'). It conveys the search/discovery nature of the tool, which differentiates it from the sibling tool names like get_skill and install_skill, though it does not explicitly name those alternatives.

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

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

The description implies usage: use this tool when you want to search the catalogue for matching skills. However, it offers no explicit guidance about when to prefer it over get_skill, install_skill, or recommend_skills, nor does it state any exclusions or prerequisites.

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