Qumge Skills

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

With no annotations, the description must carry the behavioral burden, and it does disclose the return format (markdown), the two-phase retrieval pattern, and a real payload warning ('they can be hundreds of KB'). It omits the read-only/no-side-effect nature and what happens for an invalid slug, so it is not fully complete.

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 front-loaded, and the re-call condition placed last where it is actionable. The embedded file-path instruction is caller-specific boilerplate, though it is appropriately hedged with 'or the equivalent for the user's agent'.

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 must explain returns — and it does: the SKILL.md markdown, the optional extra files, and the signal in the reply that more files exist. Combined with sibling routing, an agent has enough to call and act on the result, with only error behavior left 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?

Schema description coverage is 100%, so both parameters are already documented in the schema — including include_files returning the folder's other files and being off by default. The description largely restates that, adding only the sequencing hint that it is used on a second call, so the 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?

States a specific verb and resource ('Fetch the full SKILL.md content of one skill') and pins the identity of the target to 'the slug returned from search_skills', which cleanly separates it from the sibling search_skills that returns those slugs. An agent can tell what this returns without opening the schema.

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 routing rule (slug comes from search_skills) and a full workflow: write the markdown to the agent's skill directory, and re-call with include_files: true when the reply signals extra files. No explicit when-not-to-use statement or error/edge-case guidance, so it stops short of 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?

With no annotations, the description carries the burden of behavioral disclosure. It clearly indicates this is a read-only listing operation (via 'List') and discloses the return shape (categories and counts). It does not mention potential limitations like sorting or pagination, but for a simple list 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 two short, front-loaded sentences. The first sentence states the core function, and the second adds usage context. Every word earns its place, with no redundant or vague phrasing.

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 fully sufficient. It explains what the tool returns (categories and counts) and provides usage context. There are no hidden complexities or dependencies that need further explanation.

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

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

The tool has zero parameters, so the baseline is 4. The description adds no parameter information because none exists; the schema is empty and the description does not need to compensate for any parameter documentation gaps.

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 ('List') and resource ('skill categories'), and explicitly mentions the return content ('how many skills are in each'). This distinguishes it from sibling tools like list_bundles and search_skills, which focus on different resources or actions.

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 when-to-use guidance: 'Useful when the user is browsing rather than looking for something specific.' This implies a contrast with search_skills, but does not explicitly name alternatives or state when not to use the tool, stopping short of a full 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 carry the behavioral disclosure burden. It does well by revealing that all models are reachable with the same Qumge key (no per-vendor signup), only tool-calling models are listed, and ordering is 'best first.' These are non-obvious behaviors beyond a generic list. It does not mention pagination or error cases, but the key behavioral traits are covered.

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

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

The description is three sentences, each earning its place: the first states the core function and ordering, the second clarifies authentication, and the third sets an important constraint. It is front-loaded with the action and resource, with no fluff or redundancy.

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

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

Given the tool's simplicity and no output schema, the description adequately covers what an agent needs: what models are listed, how they are ordered, the authentication benefit, and the tool-calling filter. It does not specify the exact return fields or error behavior, but for a model-listing tool, the information provided is reasonably complete.

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

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

The schema already fully describes both parameters (limit and query) with clear descriptions, so schema coverage is 100%. The description adds minimal extra parameter-related context—it does not elaborate on how the filter works beyond what the schema says. Per baseline, a score of 3 is appropriate when the schema carries the explanatory load.

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: 'List the models this gateway can route to, best first.' It specifies the resource (models), the action (list), and adds a helpful qualifier ('best first') plus a scope restriction ('Only tool-calling models are listed'). This distinguishes it from sibling tools that deal with bundles, skills, or categories.

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

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

The description implies when to use the tool: whenever an agent needs to see available models that can be routed to, notably with the same Qumge key. It also gives an exclusion hint: models that are not tool-calling are not listed, so if you need those, this tool is not sufficient. However, it does not explicitly mention alternative tools, though none of the siblings are model-related.

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, description carries full burden. It discloses ranking method (LLM read each one), return contents (one-line summary, slug), and browse behavior when query omitted. Could mention pagination details but schema covers offset/limit; still well beyond 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 sentences, front-loaded with action and resource, includes examples and return info. Every word earns its place, no 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?

No output schema, so description must explain return values—it does (one-line summary, slug, ranked best few). Combined with schema details, the description sufficiently covers purpose, usage, behavior, and integration with get_skill.

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 parameter semantics beyond schema, mostly repeating that query is in user's words and that omitting it browses top-ranked. No significant added value for limit/offset/category.

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 an explicit verb (Search), resource (Qumge's curated catalog of agent skills / SKILL.md files), and purpose (by what the user wants to accomplish). It distinguishes from siblings by noting result includes the slug to pass to get_skill, and category param references list_categories.

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 explicit when-to-use: 'Use this whenever the user asks for a skill, tool, or capability' with examples. It also provides an alternative/next-step by mentioning the slug is for get_skill, and references list_categories for category browsing.

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