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

Annotations already declare readOnlyHint=true, but the description adds substantial detail beyond that: it clarifies the search does not call providers, create demand, or trigger payment, and that recording demand does not guarantee immediate creation. It also discloses the conditional next_action behavior. This goes well beyond the annotation's minimal signal.

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 about three sentences but every sentence earns its place: core purpose, conditional branching, and explicit caveats. It is front-loaded with the search action and efficiently communicates all necessary behavioral details without fluff.

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 there is no output schema, the description does a good job explaining what the tool returns: a match's execution.next_action in the success case, and an explicit next_action for record_missing_capability_demand in the no-match case. It also states the read-only nature. The only minor gap is not explicitly describing the structure of matches (e.g., array of objects), but the mention of execution.next_action gives enough to proceed. Overall adequate for this complexity.

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 100%: both query and limit have thorough descriptions. The tool description adds no new parameter-specific detail beyond reinforcing that the query is a natural-language task description, which is already in the schema. Baseline 3 is appropriate.

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 (search) and resource (replay-verified MISSING catalog) via natural-language query. It clearly differentiates from siblings by explaining the branching flow: on a match, continue to resolve_capability; on no match, return a next_action for record_missing_capability_demand. This makes the tool's purpose unmistakable.

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?

Explicitly says when to use this tool (when you have a natural-language task description and need a verified match) and what to do after: if match satisfies, call resolve_capability; if not, the tool itself returns a next_action for record_missing_capability_demand. This is direct guidance on the workflow and alternatives, leaving no inference required.

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