AgentTask Atlas

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond that by enumerating the payload the caller receives (verdict, install command, credentials, permissions, license, source, maintenance status), which is important since there is no output schema.

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

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

One sentence, front-loaded with the verb, resource and key, followed by the field inventory. No filler, no repetition of the title.

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 and no parameter descriptions, the description compensates by listing exactly what the card returns and how to address it. Nothing essential for correct invocation is missing for a simple one-parameter read tool.

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

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

Schema coverage is 0% for the single 'slug' parameter, so the description must carry the load. It does reasonably well by naming the identifier type and giving a concrete example value ('github-mcp-server'), which clarifies the expected slug format that the schema leaves bare.

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 (get) and resource (one catalog entry) plus the lookup key (slug) and enumerates what the entry card contains. An agent can tell it apart from list_categories and search_catalog by the by-slug single-item framing, though it never names those siblings explicitly.

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: 'by slug' suggests this is the tool for when the identifier is already known, and the example slug reinforces that. There is no explicit statement of when to prefer this over search_catalog, or what to do when the slug is unknown.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety and side-effect profile are covered structurally. The description adds the useful detail that results include entry counts and page URLs, but says nothing about ordering, pagination, or filtering behavior.

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

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

A single tight sentence with the resource front-loaded and every clause (categories, entry types, counts, URLs) carrying information. 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?

With no parameters and no output schema, the description must convey what comes back, and it does: categories, entry types, entry counts, and page URLs. It is adequate for a simple listing tool, missing only ordering/scale hints.

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, so the baseline is 4. The description correctly implies a no-argument, whole-catalog listing and adds no misleading parameter expectations.

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 the resource precisely ('dev-task categories and entry types') plus the payload (counts, page URLs), so an agent knows exactly what it returns. However, it never names or contrasts with the siblings get_entry and search_catalog, so differentiation is left implicit.

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 explicit when-to-use or when-not-to-use guidance and no mention of alternatives. Usage is only inferable from the fact that it returns a catalog-like enumeration.

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 readOnly/openWorld=false/idempotent/non-destructive, so safety is covered. The description earns credit by disclosing non-obvious behavior: which fields are matched, that common terms like postgres/e2e/scraping are synonym-expanded, and that an empty query returns the category listing. Result ordering and how limit truncates are not described.

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 purpose before the parameter mechanics, with no filler. The nested parentheticals for matching rules and slug sources make it dense but each 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 partially compensates by naming the matched fields (name, vendor, verdict, install, category), hinting at the returned entry shape. For a 3-param, no-required-arg search tool this is close to complete; only the limit/pagination behavior and result ordering remain unstated.

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 67%; query and category are documented in-schema, while limit is not. The description adds real meaning beyond the schema by explaining match fields, synonym expansion, the empty-query listing behavior, and that category accepts either a dev task or a type slug. The undocumented limit parameter is left unaddressed.

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?

'Find MCP servers and Agent Skills for a dev task' names a specific verb and resource, and the matching semantics ('every term must match name, vendor, verdict, install or category') make the scope concrete. It partially differentiates from siblings by pointing at list_categories as the slug source, but never contrasts itself with get_entry, which is the more likely 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?

It lays out three usage modes clearly: free-text query, optional category filter, and the empty-query case that lists the category. It also routes the agent to list_categories to obtain valid slugs. What is missing is any negative guidance (e.g. use get_entry for detail on a known entry).

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