Search local LangGraph documentation for relevant excerpts, source URLs, and cosine similarity scores to answer semantic queries.
Search local LangGraph docs; return excerpts, source URLs and cosine similarity.
| Name | Required | Description | Default |
|---|---|---|---|
| k | No | ||
| query | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| results | Yes | ||
| indexed_at | Yes |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety and determinism are covered by structured data. The description adds the useful fact that results include similarity scores and source URLs, but says nothing about corpus scope, freshness, or result limits beyond the k parameter.
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?
A single front-loaded sentence with zero filler; the action and the return payload lead. It is terse to the point of under-specification, but on the conciseness dimension itself it performs well.
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?
An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a retrieval tool with a sibling and fully undocumented parameters, the description omits usage routing and parameter meaning, leaving real gaps.
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 0% for two parameters, so the description must compensate and does not: it never explains what 'k' controls (result count) or what 'query' should contain. An agent can guess k from the maximum of 20, but the description provides no added meaning.
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 gives a specific verb (Search) and resource (local LangGraph docs) and even previews the return shape (excerpts, source URLs, cosine similarity). It is clear on its own, but it does not distinguish itself from the sibling read_page tool.
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?
There is no statement of when to use this search tool versus the sibling read_page, and no prerequisites or exclusions. The agent must infer the retrieval-vs-fetch distinction from the names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.