Search and read official Proa Rust web framework documentation, including rendering, RSJS islands, routing, and deployment. Public, read-only tools and Markdown resources; no account or API key required.
Scored across 2 tools
The two tools have clearly distinct purposes: search_docs finds documentation pages, while get_doc retrieves a full page by path. Their descriptions explicitly describe the search-then-retrieve workflow, leaving no realistic ambiguity.
Both names follow a consistent snake_case verb_noun pattern: search_docs and get_doc. The singular/plural difference in 'doc' vs 'docs' reflects the operation rather than inconsistent naming.
Two tools are minimal but well-matched to a documentation retrieval server: one for discovery and one for reading. It is slightly thinner than the typical 3-15 range, but each tool clearly earns its place.
The search-plus-retrieve pair covers the core documentation workflow and supports pagination through search results. A dedicated browse/list-all operation is absent, but search_docs plus resources/list largely compensates.
Read a complete official Proa documentation page as Markdown with its title, description, and canonical route. Supply a path returned by search_docs or resources/list. Only published documentation is accessible; arbitrary URLs and filesystem paths are not fetched.
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes | Published route or Markdown path, for example /docs/core/html-rendering. |
| Name | Required | Description |
|---|---|---|
| path | Yes | |
| title | Yes | |
| markdown | Yes | |
| description | Yes | |
| markdown_url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful access constraints: only published documentation is accessible, and arbitrary URLs or filesystem paths are not fetched. It could say more about failure modes or auth, but the key behavioral boundaries 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?
Three short sentences, front-loaded with the core action and format, then sourcing and restrictions. No wasted text.
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 single-parameter read tool with an output schema, the description covers purpose, valid inputs, and access boundaries. Nothing an agent needs to invoke it 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 coverage is 100% and already documents the single path parameter with an example. The description nevertheless adds value by specifying where valid paths come from (search_docs or resources/list) and what kinds of paths are invalid.
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 (read) and resource (official Proa documentation page), including the output format (Markdown) and returned metadata. It clearly distinguishes itself from the sibling search_docs by requiring a path that search_docs returns.
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?
Explicitly says to supply a path returned by search_docs or resources/list, and rules out arbitrary URLs and filesystem paths. This gives clear when-to-use and when-not-to-use guidance with the alternative tool named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search official Proa Rust framework documentation by a case-insensitive phrase. Use this to find current APIs, render patterns, RSJS guidance, and deployment instructions. Returns titles, routes, Markdown URLs, and a pagination cursor; call get_doc with a returned path for the complete page.
| Name | Required | Description | Default |
|---|---|---|---|
| q | Yes | Phrase to find in document titles, descriptions, or Markdown. | |
| limit | No | Maximum results per page; defaults to 10. | |
| cursor | No | next_cursor from a preceding search with the same q. |
| Name | Required | Description |
|---|---|---|
| total | Yes | |
| results | Yes | |
| next_cursor | Yes | Opaque cursor for the next page, or null when the result set is complete. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered; the description adds behavioral value by disclosing case-insensitive matching and the pagination handoff via next_cursor. It doesn't state ordering or ranking of results, which is a minor remaining gap.
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, each doing distinct work: what/how, use cases, and return-plus-next-step. Front-loaded with the core action and 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 full schema coverage, an output schema, and read-only annotations, the description only needs to establish scope and the get_doc handoff — both are present. Return fields and cursor mechanics are covered jointly by the output schema and the description's summary.
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; the description earns above it by adding that matching is case-insensitive and that the cursor is meant to be fed back for pagination, semantics not explicit in the schema. Limit defaults and ranges remain schema-only, which is fine.
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 (search) and resource (official Proa Rust framework documentation) with a matching constraint (case-insensitive phrase). It also distinguishes itself from the sibling get_doc by defining the search-then-fetch workflow, so an agent can pick correctly without opening either 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?
Names concrete content domains where this is the right tool (current APIs, render patterns, RSJS guidance, deployment) and explicitly routes full-page retrieval to get_doc. Missing only explicit when-not criteria, e.g. what to do for non-documentation questions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_docsearch_docs
Add one secure layer between your agents and this server.