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

Annotations already establish readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds useful context about bulk execution via ids/product_ids and lists the supported filters, but it still does not explain return shape, pagination, or behavior when required combinations like id + invoice_code are missing.

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 compact and scannable, using a bullet-like structure to list actions and filters efficiently. There is little redundant wording, though the 'Flattened action' label adds ambiguity without being elaborated.

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 tool with 15 optional parameters and no output schema, the description is insufficient. It does not state what the tool returns, how pagination works, which parameters are required for the main action, or how the 'Flattened action: invoice_transactions' relates to the other listed actions.

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 coverage, the description carries the full parameter-semantics burden. It partially compensates by mapping many parameters to actions and showing that invoice_transactions needs both id and invoice_code, but it does not explain the meaning, formats, or required constraints for several parameters such as account, cursor, and the date fields.

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 says 'Assinaturas no Guru (leitura)' and then lists many independent actions, not a single clear operation. The 'Flattened action: invoice_transactions' hint partially clarifies, but the tool's purpose remains ambiguous because it seems to cover search, get, activities, invoices, transactions, payment_types, and plans.

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?

No explicit guidance is given for when to use this tool instead of the many separate sibling tools such as guru_subscriptions_search, guru_subscriptions_invoice, or guru_subscriptions_transactions. The 'leitura' label only implies read-only usage; it does not describe situations or exclusions.

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