Use This Skill

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

Annotations only declare readOnly and openWorld; the description adds substantial behavioral content beyond them: the three verdict values (clear, review, flagged), that findings are reported per skill folder with file, line and matched text, and that non-directory skills are fetched and scanned live. This is exactly the extra context annotations cannot convey.

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 short sentences, front-loaded with the purpose, then input forms, then return shape and the live-fetch caveat. No filler; every clause carries information an agent needs.

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

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

With no output schema, the description takes on the return-value burden and does so: verdict categories plus per-finding file/line/text. Combined with accepted input forms and the live-scan note, nothing material is missing for a one-parameter 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% and the schema already documents the slug-or-URL format, so baseline is 3. The description still adds real meaning by enumerating accepted URL granularities — repository root, a folder inside one, or a SKILL.md file — which the schema's single example does not make explicit.

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 a specific verb and resource ('Safety-check a skill') and bounds it to the pre-install decision. It is clearly distinguishable from siblings like get_skill (retrieval) and search_skills (discovery), which are referenced as sources rather than duplicates.

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?

Gives a clear usage context ('before installing it') and names the two accepted input routes, pointing at search_skills for slugs. It stops short of saying when to prefer this over get_skill or get_proof, but the pre-install framing is explicit enough to route an 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the useful fact that 'every proof is open' (public visibility), but says nothing about behavior on an unknown slug or the response shape.

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

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

A single compact sentence with no filler, and the defining content (what a proof is) is front-loaded. It is slightly under-specified rather than verbose, but structurally efficient.

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

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

For a simple read-only fetch with no output schema, listing the returned fields is genuinely helpful. However, the omission of the slug parameter's meaning and any error behavior leaves gaps an agent needs to call 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?

There is one required parameter, slug, at 0% schema description coverage, and the description never mentions it — not what a slug is (skill identifier vs. proof identifier), nor its format. With a low-coverage single param, the description should compensate and does not.

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 enumerates what a proof contains (fixed brief, model, skill commit, result-page links), which conveys the resource well, but it never states the action or the lookup key. It reads as a noun definition rather than 'retrieve the proof identified by slug', and it does not distinguish itself from siblings like check_skill or order_proof.

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?

There is no guidance on when to call this versus check_skill, get_skill, or search_skills, and no prerequisite (e.g. needing a known slug) is stated. The agent must infer usage entirely.

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 cover the safety profile (readOnlyHint, openWorldHint=false), yet the description adds real value: it discloses that SKILL.md text is returned only when the license allows it, and it pre-empts prompt injection by framing that text as data, not instructions. It does not say what happens for an unknown slug or an inaccessible license.

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 the core action and the payload inventory, then the safety caveat. No filler, and the injection warning is placed where a reader will reach it before using the output.

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 usefully enumerates the returned fields and flags the conditional license dependency. The remaining gap is failure behavior — missing slug, unpublished skill, restricted license — which an agent would want to know before relying on the result.

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?

One required parameter at 0% schema coverage, so the description must carry the load. Saying 'by slug' establishes the identifier's role but not its format, source, or case sensitivity, which is the information an agent actually needs to form a valid call.

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 a specific verb and resource — 'Full details for one skill by slug' — and enumerates exactly what comes back (install command, source link, license, safety scan, SKILL.md text). It implies the split with search_skills/check_skill through 'one skill' and 'full details', but never names a sibling to make the distinction explicit.

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?

Usage is only implied: fetch details once you already have a slug. There is no guidance on when to prefer this over check_skill or search_skills, and no stated precondition such as whether the slug must come from search results.

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, so the safety profile is covered. The description adds real domain meaning by defining what a proof is — the same brief built with and without the skill as two live pages — which helps the agent interpret results, but says nothing about return shape, ordering, or size.

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

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

A single compact sentence with the scoping qualifier front-loaded and no wasted words. It is a noun fragment rather than a sentence with a verb, which slightly weakens the lead, but nothing is padded.

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 list tool with no output schema, the description should say roughly what comes back (skill names, ids, links to the two proof pages). It explains the concept behind 'proof' but leaves the result shape entirely unspecified.

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

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

The tool takes zero parameters, and the empty schema is fully documented, so there is nothing for the description to disambiguate. Baseline 4 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 names the resource precisely (skills having a published proof) and scopes it with 'published', so an agent knows it is a filtered listing rather than all skills. It never uses an explicit verb like 'list', and it does not name the sibling it differs from (search_skills, get_proof), so it falls just short of 5.

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

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

There is no statement of when to use this versus search_skills (broader lookup) or get_proof (retrieve one proof). The only signal is the implicit 'only proven skills', leaving the agent to infer the selection condition.

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 frames this as the mechanism by which a skill becomes 'proven and listed' with a $49 charge, i.e. a state-changing, monetary transaction, while annotations declare readOnlyHint=true and openWorldHint=false. That is a direct conflict about side effects, and the description never clarifies whether it spends money, mutates state, or merely mints a link.

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

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

Two short sentences, front-loaded with the outcome and price, and the return value noted last. Efficient, though the phrasing is task-narrative rather than spec-like.

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 paid workflow entry point with no output schema and no annotation reliability, it omits prerequisites (does the repo need to exist? does check_skill come first?), what the returned link does, whether ordering is idempotent, and how to supply the skill 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?

There is one parameter, skill_github_url, with 0% schema description coverage, and the description never mentions it, so nothing tells the agent what URL form is expected or whether it is optional/required. With low coverage the description is obliged to compensate and does not.

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 clear outcome: a skill author gets their skill proven and listed, at a stated price ($49, automatic), and receives an order link. The verb 'order' comes from the title rather than the body, and no sibling (get_proof, list_proven, check_skill) is named for contrast, so it stops short of a 5.

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

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

It implies the audience (a skill author wanting their own skill listed) but gives no explicit when-to-use or when-not, and never routes the agent away from get_proof/list_proven or tells it whether ordering is a prerequisite for those. The agent must infer all sequencing.

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, so the safety profile is covered. The description adds useful behavioral context by listing the returned fields, including install command and proof existence, which matters because no output schema exists.

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 compact sentences, front-loaded with the purpose and followed by the return fields. Every sentence contributes useful information without 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?

The description covers purpose and return fields, which is helpful given the lack of an output schema. It is still incomplete for a search tool because it does not clarify category filtering, limit behavior, or when to use it over adjacent skill-retrieval tools.

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 moderate at 67%, and the description adds little parameter meaning beyond the schema. It loosely implies a task/query focus but does not explain the category filter or the limit parameter, leaving the latter undocumented in both schema and 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 states a specific verb and resource: 'Find agent skills for a task.' It is clear what the tool does and what metadata it returns, but it does not explicitly distinguish itself from siblings like get_skill or list_proven.

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

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

The phrase 'for a task' implies this is a discovery/search tool, so usage is reasonably inferable. However, it gives no explicit when-to-use guidance, no exclusions, and does not mention alternatives such as get_skill for known skills.

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