List public documents with optional locale, area, and exact-tag filters. Use the opaque cursor for pagination.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | ||
| area | No | ||
| limit | No | Number of documents to return (default 50, maximum 100). | |
| cursor | No | ||
| locale | No |
| Name | Required | Description | Default |
|---|---|---|---|
| documents | Yes | ||
| generation | Yes | ||
| next_cursor | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, non-destructive behavior. The description adds value beyond these by specifying that only public documents are returned and that the cursor must be treated as opaque, which are useful behavioral constraints not present in the annotations.
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-load the core purpose and then add the single most important operational detail (opaque cursor). There is no filler or repetition of schema fields, 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 description, combined with a read-only annotation set, an output schema, and the limit parameter's schema-level description, is adequate for an agent to make a correct list call. The main gap is the lack of explicit routing guidance between this tool and its search/related-document siblings.
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?
With only 20% schema description coverage, the description must compensate for parameter meaning. It identifies locale, area, and exact-tag filters and explains the cursor's role, but it does not provide accepted value formats or further detail for area/locale/tag, leaving some semantics underspecified.
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 a specific verb and resource ('List public documents') and identifies the key filtering dimensions (locale, area, exact-tag), which clearly conveys the operation. It does not explicitly contrast with sibling tools like search_documents or read_document, so it stops short of full differentiation.
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 for enumerating public documents with optional filters and pagination, but it does not state when to prefer list_documents over search_documents or related_documents, nor does it state any exclusions. The usage context is inferable rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: listing metadata, reading full content, reading a specific section, finding related documents, and searching. Even the closest pair (read_document vs read_document_section) is clearly separated by scope and parameter usage.
Most names follow a clear verb_noun pattern (list_documents, read_document, search_documents), with read_document_section extending the pattern descriptively. related_documents is the one outlier because it uses an adjective/noun phrase rather than a verb, though it is still understandable.
Five tools cover the natural read-only document workflow without redundancy or bloat. The count is well-scoped for a public knowledge/documentation server.
The surface supports discovering documents, reading full documents or individual sections, searching, and navigating related content. Metadata and outline are included in read_document, so there are no obvious gaps for consuming public documentation.