classifier.dev docs

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is established. The description adds valuable behavioral context: it returns a copy-pasteable example and notes the output is the 'exact request shape,' which helps an agent know what to expect. It does not contradict annotations and adds relevant information beyond the structured hints.

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 redundancy. The first sentence states the primary function and lists the clients; the second provides the usage context. It is front-loaded with the core purpose and 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?

The tool is simple with only 2 parameters and an output schema exists, so the description does not need to explain return values. The description covers what the tool does, when to use it, and the client options. There are no missing elements that would prevent an agent from calling 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?

The input schema covers 100% of parameters with clear descriptions (client enum and multi_label boolean). The description does not add additional parameter semantics beyond what the schema provides; it only mentions 'given client' without extra detail. Since schema coverage is high, 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 tool's purpose: returning a copy-pasteable example for specific clients (curl, javascript, python, cli, mcp). It uses a specific verb ('return') and names the resource (classifier.dev) and the exact set of clients. It also distinguishes itself from sibling doc tools by focusing on request shapes rather than documentation.

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 states when to use the tool: 'Use this when you are about to write integration code and want the exact request shape rather than reading the whole reference.' This provides a clear condition and contrasts with an alternative (reading the whole reference), which is likely covered by sibling tools like read_doc.

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 establish readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral context by enumerating the document categories and explicitly framing this as the first step in a list-then-read workflow, going beyond what the annotations state.

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 front-loaded with the action and scope, then gives the output fields and the recommended next step. The longer enumeration of document categories is purposeful rather than padded because it tells the agent exactly what content will be listed, and there is no redundant or filler wording.

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 list tool with one optional and fully documented parameter, the description covers scope, output composition, and usage order. The annotations carry the safety semantics and an output schema exists, so nothing an agent needs to invoke this tool 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?

Schema description coverage is 100%, and the sole optional filter parameter is fully documented in the input schema ('documents whose id, title or section headings contain this text'). The description adds no additional parameter semantics, so the baseline score 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 uses a specific verb and resource ('List every classifier.dev document') and names the exact set of documents included, making the tool's scope unmistakable. It also states the returned shape (id, title, section headings, size) and points to read_doc as the follow-up, helping distinguish it from the sibling that retrieves individual documents.

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 gives an explicit workflow instruction: 'Call this first, then read_doc for the one you need,' so an agent knows when list_docs is the right entry point. It does not, however, contrast list_docs with search_docs or state when search_docs would be preferable, which leaves some usage ambiguity among the sibling 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds useful behavioral detail: section is a case-insensitive prefix match on a heading. It does not cover edge cases like a missing section match or the exact return format, but the annotations carry the main safety burden.

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 short and front-loaded with the core behavior, then gives the section usage. Its main flaw is repeating the full id enum that is already present in the schema, which adds minor redundancy but does not seriously hurt usability.

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 tool with two parameters, the description covers the main choices: which document and optional section. It lacks an explicit statement of the return format, but 'return one document in full' is sufficient for most agents, especially with the strong annotations.

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 the baseline is 3. The description adds value by explaining the section parameter's matching behavior and when to use it, which is not fully specified in 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 verb and resource: it returns one document in full or a single section. The explicit id list and the contrast with listing/searching make the tool's purpose 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?

It gives clear within-tool guidance: use the section parameter when the whole document is more than needed. It does not explicitly name sibling tools like list_docs or search_docs for when to use those instead, but the retrieval intent is obvious from the first sentence.

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, and destructiveHint=false, so the safety profile is covered. The description adds useful runtime behavior: results are paragraphs, not whole documents, and all query words must appear. This gives an agent a realistic expectation of the output without an 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?

Three short sentences, each earning its place: purpose, return shape, and usage guidance. The key constraint (all query words must appear) is stated compactly.

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 search tool, the description covers what it does, what it returns, and when to use it. The only minor gap is the unstated meaning of 'limit,' and the absence of an output schema is mitigated by the description's return-value 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 schema describes 'query' and the description reinforces the all-words-must-match semantics, but the 'limit' parameter has no semantic description in either the schema or the description. With only 50% schema description coverage, the description partially compensates but does not fully document the other parameter.

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 opens with a specific verb and resource: 'Full-text search across every classifier.dev document.' It also states the distinctive return shape (paragraphs with document and section), which differentiates it from sibling tools like list_docs and read_doc.

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 last sentence explicitly tells the agent when to choose this tool ('Use it for a specific question') and gives concrete examples, contrasting with 'reading whole documents.' It does not explicitly name sibling tools or state when not to use it, but the usage context is clear.

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