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

The description adds real behavioral context beyond the annotations: batch size limit of 100, the restriction that lead_ids only supports archived/trabalhado, and the reassurance that nothing is deleted. That last claim sits in mild tension with destructiveHint=true (archiving and overwriting CNPJ/message are state-changing), and nothing is said about partial-failure behavior or permissions beyond the schema's admin note.

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?

Three tight sentences with the main capability front-loaded before the batching and single-lead constraints. Nothing is padded, though the mixed Portuguese/English phrasing and the emoji header add minor noise for a non-Portuguese model.

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 7-parameter mutation tool with no output schema and no required params, the description covers the operations, the batch/single split, and the non-deletion guarantee. It stops short of explaining return values or what happens when lead_ids mixes valid and invalid operations, but annotations and schema carry most of the rest.

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 already 100%, so the baseline is 3; the description earns an extra point by adding the constraint that lead_ids is capped at 100 and only supports archived/trabalhado, a restriction the schema does not state. The CNPJ/message-require-lead_id rule largely repeats the schema.

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 names a specific resource (Garimpo/domain-checker leads) and enumerates the concrete operations: archive/restore, mark as approached or not, and correct CNPJ or message. It is unambiguous what the tool does, though it never names a sibling (e.g. tag_domain_checker_leads, add_domain_checker_leads) that would help an agent route between them.

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?

Usage rules are stated at the parameter level: use lead_ids for many leads (max 100, only archived and trabalhado), and use lead_id one at a time for CNPJ and message edits. However there is no guidance on when to pick this tool over related siblings such as tag_domain_checker_leads or rename_domain_checker_tag, so the agent must infer alternative selection.

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