Find relevant passages in a local document corpus by running dense semantic vector search with pinned multilingual embeddings, scoped to a run and optional sources.
Perform dense semantic vector search across the local document corpus using pinned multilingual embeddings.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes | ||
| run_id | Yes | ||
| sources | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden, and it mostly restates the mechanism. It does not explain result ordering, how limit interacts with ranking, how run_id scopes the corpus, or whether/how sources filters narrow the search — the traits an agent would need to invoke it confidently.
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 well-formed sentence with no wasted words and the core action front-loaded. It is appropriately sized, though its brevity is a symptom of under-specification rather than disciplined concision.
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 described, but for a 4-parameter search tool with 0% schema coverage, zero annotations, and many competing search siblings, the description leaves too much unspecified — parameter meaning, usage routing, and result behavior are all 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% across 4 parameters, so the description is expected to compensate and does not. run_id, sources, limit, and query all lack any meaning beyond their names; the intent of 'run_id' in particular is entirely opaque from this text.
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 states a specific verb and resource ('dense semantic vector search across the local document corpus') plus a mechanism ('pinned multilingual embeddings'), so the agent knows exactly what the tool does. It fails to differentiate from close siblings like search_documents, search_source, or find_counterevidence, which is the only thing keeping it from a 5.
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 semantic search versus the many other search/retrieval siblings (search_documents, search_source, find_counterevidence). No contexts, prerequisites, or exclusions are given; the agent must infer the use case entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.