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

The description adds significant behavioral context beyond annotations: it reveals the tool supports multiple legacy API versions with raw field differences, accepts bulk transaction_ids, and uses a 'data' JSON parameter for filters. Annotations already declare readOnly, idempotent, and non-destructive, which the description reinforces without contradiction. The additional details (version sharing, bulk, filter mechanism) provide a comprehensive behavioral picture.

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 verbose and mixes Portuguese and English. It lists actions redundantly (e.g., actions list then flattened action note). The bulk support note is useful but could be integrated. The structure is not front-loaded with the core purpose, requiring multiple reads. Could be more concise and structured.

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 complexity (4 parameters, no output schema, 0% parameter descriptions), the description is insufficient. It does not explain the return format, pagination behavior, or the exact role of each parameter. The agent lacks details to correctly invoke the tool, especially for 'account' and 'transaction_id'. Annotations help but do not cover parameter usage.

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 must explain parameter meanings, but it only partially does so. It explains that 'data' holds list filters (count, page, status) and 'transaction_ids' enables bulk execution. However, 'account' and 'transaction_id' are not explained, and the relationship between parameters (e.g., when to use transaction_id vs transaction_ids) is unclear. This leaves significant ambiguity for the agent.

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 it is for reading legacy Pagar.me transactions (V1-V4) and specifies the flattened action as 'list_transactions'. It distinguishes from sibling tools like pagarme_legacy_get_transaction by mentioning the separate get action and from other legacy list tools by naming them. The purpose is specific, actionable, and well-differentiated.

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 indicates this tool is active when using legacy ak_ keys (accounts not migrated to V5), providing a clear trigger condition. It lists related actions (list_subscriptions, etc.) implying alternatives, but does not explicitly state when to use this tool over siblings or provide when-not scenarios. Context is clear but lacks exclusions.

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