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

Annotations already declare readOnlyHint=true, which the description supports by being a search operation. The description adds valuable behavioral context: the curated coverage set, the 'no COT data' caveat, the search broadening behavior (in the param description), and the return of codes and categories. This goes beyond the annotation-provided safety/read-only signal, though it doesn't detail exact output structure or pagination beyond maxResults.

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: three sentences that front-load the action, state the scope and coverage limitation, and clarify the return value and its intended follow-up. No wasted words; every sentence provides necessary information for using the tool.

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 simple 2-optional-parameter profile, no output schema, and annotations covering safety, the description is complete. It covers what the tool searches, what it returns, coverage boundaries, and how to use it in the broader workflow (before GetCftcPositioning). A small gap is the lack of the exact output shape, but 'codes and categories' suffices for a discovery 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 input schema already has thorough descriptions for both parameters (query and maxResults) with examples and default/max values, giving 100% schema coverage. The main description reiterates that the query can be a name, code, symbol, etc., and that omitting it lists all, which adds value but does not significantly exceed what the parameter descriptions already explain. Baseline 3 is appropriate given the schema does the heavy lifting.

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 searches tracked CFTC futures contracts by multiple identifiers (name, market code, common name, symbol) and can list all when no query is given. It uniquely distinguishes itself by explicitly directing the agent to use it for discovering market codes before calling GetCftcPositioning, separating it from the many Get* and Search* siblings.

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 explicit guidance on when to use the tool, including the directive to 'discover market codes before calling GetCftcPositioning'. It also explains the coverage limitation (only ~35 curated contracts, markets outside have no COT data), helping the agent decide if this tool is applicable. The 'omit the query to list all' also clarifies a use case.

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