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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so safety is covered. The description adds domain context: the catalog scope (only A1, e-CPF/e-CNPJ), which is perhaps more a constraint than behavior. It doesn't describe result volume, pagination, or whether results reflect live inventory, but with annotations covering the safety profile a 3 is appropriate.

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?

A single dense sentence that front-loads the resource and scope, with a short second clause for the filter. No filler, though the parenthetical about A1 types is slightly information-dense but earns its place by delimiting the catalog.

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 read-only search with an output schema absent, the description should convey what results include (it does: price, validity, requirements, required fields) but doesn't say how many, whether paginated, or what to do next. Annotations cover safety, but return-shape hints are thin; adequate but with clear gaps.

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 coverage is 100%, so the query parameter is fully documented in the schema. The description gives helpful examples of filter values ('cnpj', 'pessoa física', 'mei') that illustrate expected inputs, adding marginal value over the schema. Baseline 3 is correct when the schema does the heavy lifting. Note the examples may leak into data values rather than keys.

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?

States a specific verb+resource: lists digital certificates for sale with price, validity, requirements. It also scopes the catalog (only A1, e-CPF and e-CNPJ), which distinguishes it from get_product. It doesn't explicitly contrast with get_product, but the plural/list nature of search vs. single-item get is reasonably clear.

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?

No when-to-use guidance. It doesn't say to use this search to discover products before calling get_product with an ID, nor when to prefer it over get_policies. The optional filter hint implies discovery usage but no explicit routing.

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