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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description doesn't need to repeat safety. The description adds behavioral detail: date range format (YYYY-MM-DD), keyword matching (partial, case-insensitive on description), and filtering by card/bank. It doesn't mention pagination or return format, but with no output schema and a read operation, this is acceptable. The description complements annotations without contradicting them.

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 a single concise sentence, which is efficient and front-loaded. It provides all key information in a compact form. It doesn't waste words, though it could be slightly clearer about parameter specifics. For a tool with five parameters, this length is appropriate.

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 tool's complexity (5 optional parameters, no output schema, no enums), the description covers the essential aspects: what it does, how filtering works, and the date format. It doesn't explain return structure, but since there's no output schema and it's a straightforward list operation, the description is reasonably complete. It could benefit from mentioning whether results are paginated or ordered, but overall it's adequate.

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 description coverage is 0%, so the description carries the entire burden for parameter semantics. It explains the keywords parameter (partial match, case-insensitive on description), and mentions card and bank/pagador filters. However, it doesn't detail the date format for start_date/end_date beyond the interval mention, and payment_bank is partially described as 'banco/pagador'. The description adds value but could be more specific about each parameter's format and allowed values, especially since the schema itself is bare with no types descriptions.

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's purpose: listing transactions in a date range with optional filtering by keywords, card, and bank/payer. It uses a specific verb (retrieve/list) with a clear resource (transactions) and distinguishes itself from sibling tools like poupa_add_transaction, poupa_update_transactions, and poupa_delete_transactions_by_filter.

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 implies usage context: it's a retrieval tool with optional filters, and the date range is specified. However, it does not explicitly state when to use this tool versus alternatives like poupa_get_balance or poupa_memories. The presence of complementary tools (like add, update, delete) suggests it's the read counterpart, but that's implicit. It's clear enough for basic usage but lacks explicit 'when not to use' guidance.

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