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

The description adds behavioral context beyond annotations: it states the tool is non-destructive (matching destructiveHint: false) and limited to 'contas sk_'. It also mentions bulk execution via charge_ids. However, it does not disclose authentication requirements, rate limits, side effects, or what happens on failure. The mixed-language note about 'não-destrutivas' is helpful but the flattening note is confusing.

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 poorly structured: it mixes Portuguese and English, uses dashes without consistent formatting, and includes a confusing 'Flattened action: capture' line. The list of actions and optional data is helpful but presented in a cluttered manner. It could be significantly condensed and clarified.

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 multi-action nature of the tool (as described), the lack of output schema, and minimal annotations, the description is incomplete. It does not explain how to select an action (no action parameter), what the return value looks like, error cases, or whether actions are idempotent. The bulk support mention is good but insufficient for an agent to use the tool reliably.

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?

With 0% schema description coverage, the description partly compensates by explaining that charge_id is the key identifier, data can include fields like amount or due_at, and charge_ids enables bulk. However, the 'account' parameter is not mentioned, and the mapping between actions and data content is incomplete. The description adds value but not comprehensive semantic coverage.

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 tool name 'pagarme_charges_write_capture' implies a single action (capture), but the description lists multiple actions (capture, retry, confirm, update_due_date, etc.) without clarifying which one this tool performs. The 'Flattened action: capture' line conflicts with the listed actions, making the purpose vague. Sibling tools exist for specific actions (e.g., pagarme_charges_write_confirm), yet this description lumps them together.

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 does not provide clear guidance on when to use this tool versus its siblings. It mentions bulk support and required charge_id but fails to explain why one would choose this over, say, pagarme_charges_write_retry. No when-not-to-use or alternative suggestions are given.

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