semantic_search

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

With no annotations, the description carries full burden. It discloses that 'query' is embedded locally, uses pgvector, nearest rows are returned without the embedding, and mentions PII refusal. Missing details on error handling or performance, but sufficient for understanding core behavior.

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 exceptionally concise—6 sentences with no fluff. Front-loaded with the core purpose, every sentence adds essential context (prerequisites, behavioral notes, limitations).

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 complexity of a vector search tool with 4 parameters and an output schema present, the description covers the algorithm and prerequisites but lacks details on parameters (especially 'filters') and fails to explain the configuration requirement for the entity. Adequate but not comprehensive.

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 0%, so description must explain parameters. It mentions 'query' is embedded and that closest rows are returned (implying 'k'), but does not describe 'entity' beyond being the target, nor 'filters' (pre-filtering) or 'k' explicitly. This leaves ambiguity for the agent.

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 vector similarity search over an entity's embedding column using pgvector. It specifies the action (search) and resource (entity's embedding column), and distinguishes from typical retrieval by noting the embedding itself is not returned.

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 prerequisites: entity must have a 'search' config and a local embedding model, and it's PostgreSQL-only. However, it does not explicitly compare with sibling tools like 'get_records' to guide when to use this tool over alternatives.

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