smart_search

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals the two-stage behavior (interpret then search), the return of plan and results, and the presence of expansions in the plan. It does not discuss side effects, authentication, or rate limits, but for a search tool these are typically not critical. The description adds meaningful context beyond a generic 'search'.

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 well-structured and efficient. It front-loads the core purpose and then adds a useful note about the plan/results and alternative tool. The Args section is compact but informative. It is slightly verbose with the explanatory paragraph, but each sentence adds value; no filler.

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?

For a tool with four parameters and an output schema, the description is quite complete. It explains the return of plan and results, mentions expansions, and covers all parameters. It does not describe the output schema structure, but that is covered by the output schema itself. It lacks explicit error-handling notes, but that is not a major gap for a search tool.

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?

The description provides detailed parameter semantics in the Args section: it explains that query is the user's natural-language request with no need to strip constraints, api is optional and catalog-specific, page is 1-based, and page_size defaults to the catalog's configured size. Since the schema itself has no descriptions (coverage 0%), the description fully compensates, making parameter intent crystal clear.

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's function: 'Interpret a natural-language query with Bedrock, then run the search.' It identifies the resource (a catalog search) and the distinguishing behavior (natural-language interpretation). It also contrasts with sibling tool catalog_search by noting the ability to re-run with it, making the purpose unambiguous.

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 concrete guidance: it explains that the tool returns the plan and results so you can verify inferred filters and re-run with catalog_search if interpretation is off. It also mentions expansions as alternatives when results are thin. This gives clear context for when to use this tool vs. alternatives, though it does not explicitly list exclusions for all siblings (e.g., understand_query, list_catalogs).

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