agentdocs-mcp

Semantic search

semantic_search

Read-only

Find documentation by meaning instead of keywords: type a natural-language question and get pages ranked by semantic similarity. Pages are embedded automatically after each save.

Instructions

Search a workspace by meaning, not keywords — ask a natural-language question (e.g. "how do we handle billing retries?") and get the most relevant pages ranked by similarity. Pages are embedded automatically after each save. Requires a Pro workspace; the response 'mode' is "semantic" when active, or "fulltext_fallback" if semantic search is not configured on the instance (results are still returned).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "workspace": "<workspace>",
      "query": "<query>"
    },
    "name": "semantic_search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	Yes	A natural-language question or description (max 1000 chars)
`workspace`	Yes	Workspace UUID or workspace slug

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.9.2Aug 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=true and openWorldHint=false. The description adds important behavioral traits: pages are embedded automatically after each save, a Pro workspace is required, and the response mode can be 'semantic' or 'fulltext_fallback' depending on configuration. These go well beyond the structured annotations and help the agent anticipate variable responses.

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

Conciseness5/5

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

Three sentences, each carrying distinct information: core purpose, embedding behavior, and configuration-dependent response. No redundancy, no filler; the description is front-loaded with the primary use case.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since there is no output schema, the description reasonably summarizes what is returned ('most relevant pages ranked by similarity') and explains the response mode. It omits details like result count or pagination, but for a two-parameter, read-only search tool this is sufficient. It also covers the Pro requirement and fallback, making the tool's behavior fairly predictable.

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

Parameters4/5

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

The input schema already covers both parameters at 100%, so the description's job is to add nuance. It provides an example query and emphasizes 'by meaning' to clarify the query intent, which is a meaningful addition to the schema's terse 'natural-language question' description. The workspace parameter isn't elaborated further, but the schema already handles it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Search a workspace by meaning, not keywords', which is a specific verb+resource+method that clearly distinguishes it from keyword-based siblings like search_docs. The example query and 'ranked by similarity' further pin down the semantic nature.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It contrasts with keyword search ('not keywords') to signal when semantic search is appropriate, and states a prerequisite ('Requires a Pro workspace'). The fallback explanation ('fulltext_fallback') also gives context for when results may be returned even without semantic configuration. However, it never explicitly names an alternative tool, so it doesn't fully reach a 5.

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