Semantic Search (local module)

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

No annotations are provided, so the description carries full burden. It discloses gating, visible degradation when unavailable, and required dependencies. This is good, but could mention that it is read-only and does not modify data, though inferred. No contradictions.

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?

The description is two sentences, front-loaded with purpose and key technical details. It is efficient but somewhat dense; could be slightly more structured, but overall concise and informative.

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?

Given the tool's complexity (5 params, nested object, no output schema), the description is highly complete. It covers embedding method, gating, degradation behavior, prerequisites, and even hints at format. No critical gaps for an AI agent to use the tool correctly.

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 60%, and the description adds meaning by explaining that query is embedded locally, module pinning, and that filter are pre-filters applied before ranking. This adds value beyond the schema, especially for the filter object and format.

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 the tool does vector recall over installed local data modules with local embedding and cosine similarity. It distinguishes from siblings like search_cases and search_legislation by specifying 'local data modules' and the embedding process, making the purpose unique.

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?

The description provides clear context on when the tool works (gated on local embedder installation and module descriptor matching) and lists prerequisites. However, it does not explicitly contrast with sibling tools or state when not to use it, missing some exclusion guidance.

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