cfpb_search_complaints

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

Beyond the readOnlyHint annotation, the description adds useful behavioral specifics: the 13M+ record scale, the fuzzy auto-retry behavior for company names with a concrete 'Wells Fargo' example, and the fact that results include company responses. It doesn't disclose pagination behavior or rate limits, but the annotation already signals a safe read operation and the added details are substantive.

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 opens with the core purpose, then efficiently adds high-value details: record volume, return content, fuzzy-match behavior, and product options. No filler or redundant restatement of the tool name appears; each sentence contributes to the agent's understanding.

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 14-parameter read-only search tool with no output schema, the description sufficiently covers the main search dimensions, return type, dataset scope, and a non-obvious company-name behavior. It doesn't mention pagination or default result limits, but those are already present in the schema, and the description plus schema provide enough context for reliable invocation.

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?

Since schema description coverage is 100%, a baseline of 3 is appropriate. The description adds meaningful value for the company parameter by explaining the auto-retry fuzzy matching behavior, and it reinforces product parameter choices with a list of valid values. Most other parameters are already well documented in the schema, so the extra contribution is modest but genuine.

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 names the action ('Search') and the resource ('CFPB consumer complaint database'), and enumerates the main filter dimensions and return type ('individual complaints with company responses'). It does not explicitly distinguish this from sibling tools like cfpb_complaint_detail or cfpb_complaint_aggregations, so it falls just short of full sibling differentiation.

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 appropriate use by stating what dataset is searched and what results look like, which gives the agent a sense of when to invoke it. However, it never names alternatives such as cfpb_complaint_aggregations for aggregate views or cfpb_complaint_detail for individual complaint detail, so the guidance is context-only rather than explicit when/when-not guidance.

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