PG search more like this

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

Beyond the readOnlyHint annotation, the description explains that optional tuning args are omitted from the SQL if not provided, letting upstream defaults apply. It also requires the pg_search extension and specifies the return shape. Some details like performance implications are missing, but overall good transparency.

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 concise and well-structured, front-loading the core purpose and following with necessary details. Every sentence adds value without repetition.

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 (15 params, 5 required), the description covers essential aspects: mechanism, required params, optional tuning args, return shape, and extension requirement. It references the output shape from a sibling tool, which aids completeness. Missing error conditions or document existence handling, but sufficient for most use cases.

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?

With only 7% schema description coverage, the description adds significant value by explaining the role of document_id, enumerating the nine tuning args, and clarifying that they are optional kwargs. It compensates well for the sparse schema descriptions.

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 finds rows similar to a seed document using specific mechanisms (pdb.more_like_this + @@@). It distinguishes itself from sibling tool pg_search_run by noting it returns the same hit shape.

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 implies usage for text similarity based on a seed document, but does not explicitly state when to use this tool versus alternatives like pg_search_run, vector_search, or fuzzy_search. No when-not or exclusion criteria are provided.

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