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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds that the tool uses legacy ak_ keys, supports bulk via transaction_ids, and that field differences between V1-V4 appear raw in payload. No contradictions with annotations.

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 lists many actions and includes some redundancy (e.g., 'Flattened action'), making it longer than necessary. Key information is present but could be more streamlined.

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?

The description lacks explicit details about the return value (e.g., single transaction object) beyond noting raw version differences. Given no output schema, more completeness would be helpful.

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?

The input schema has 4 parameters with 0% description coverage. The description adds meaning for transaction_id (implied required) and transaction_ids (bulk support) and filters via data, but does not describe the account parameter. This provides moderate added value beyond 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 clearly states the tool reads legacy transactions from Pagar.me API V1-V4, and specifies the get_transaction action requires a transaction_id. It distinguishes from sibling tools like pagarme_legacy_list_transactions by focusing on a single transaction retrieval.

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 provides usage context (when connection uses ak_ key, non-migrated to V5) and lists actions including get_transaction. However, it does not explicitly state when to use this tool versus other legacy tools like list_transactions, though the 'Flattened action' helps.

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