Semantic search across a project's documentation. Returns chunks ranked by relevance. Requires the server to have semantic search enabled.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural-language search query | |
| top_k | No | Max results (1-50, default 10) | |
| project | Yes | Project slug (e.g. "nextjs", "react") | |
| version | Yes | Version string or "latest" | |
| token_budget | No | Max tokens to budget for results (default 4096) |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context beyond annotations (readOnlyHint, openWorldHint) by disclosing the server-side requirement for semantic search. It does not contradict 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 concise sentences that front-load the purpose and then add the prerequisite. Every sentence is necessary 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?
For a search tool with 5 parameters fully defined in schema and no output schema, the description gives sufficient context (semantic search, relevance ranking, server requirement). Could mention how top_k and token_budget affect output, but overall 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?
Input schema has 100% description coverage, so parameters are already well-documented. The description does not add extra meaning or context for any parameter, resulting in a baseline score.
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 it performs 'semantic search across a project's documentation' and returns 'chunks ranked by relevance', specifying the verb (search) and resource (project docs). It distinguishes from siblings like list_projects and resolve_docs by focusing on semantic search.
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?
Only mentions a prerequisite ('Requires the server to have semantic search enabled'). No guidance on when to use this tool versus siblings (list_projects, list_versions, resolve_docs) or when not to use it.
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 has a clearly distinct purpose: listing projects, listing versions, resolving documentation URLs, and semantic search. No overlap exists.
All tools follow a consistent verb_plural pattern (list_projects, list_versions, resolve_docs, search_docs), making them predictable.
With 4 tools covering project discovery, version exploration, artifact retrieval, and search, the count is well-scoped for a documentation server.
The tool surface covers the main read-only operations for documentation projects. A minor gap is the lack of project metadata retrieval beyond versions, but it is sufficient for most use cases.