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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds 'leitura' (read) which is redundant, but it does mention 'Bulk support: accepts ids, product_ids for batched execution'—a useful behavioral trait not in the annotations. However, it omits other behavioral details like pagination behavior, rate limits, or what happens when multiple actions are implied, so it adds only some value beyond the 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 is dense and relatively concise, packing many actions and filter names into a single paragraph. However, it is not well front-loaded: the first phrase 'Assinaturas no Guru (leitura)' is broad and the action list is a run-on structure with semicolons. It attempts to convey a lot but sacrifices clarity, making it hard to parse. A clearer structure with separated action definitions would improve readability.

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?

This tool has 15 parameters, no output schema, and a complex multi-action behavior. The description provides only a partial map of actions to parameters and does not explain the tool's default behavior, how the flattened action works, or what the return values look like. The presence of many sibling tools that seem to overlap makes the description even less complete for an agent to select and invoke the tool correctly.

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 schema has 15 parameters with 0% description coverage, so the description must compensate. The description does map some parameters to actions (e.g., 'search (filtros: subscription_status, product_id, contact_email/contact_doc/contact_name, started_at_ini/end, last_status_at_ini/end, cursor)'), but many parameters like 'account', 'product_ids', 'ids', and 'invoice_code' are only mentioned in passing. The description doesn't fully explain the meaning of each parameter or how they interact with the different actions, leaving the agent uncertain about which parameters are relevant for which invocation.

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 states 'Subscriptions in Guru (read)' and lists multiple actions (search, get, activities, invoices, invoice, etc.), but it is unclear which action the tool is meant to perform given its name 'guru_subscriptions_invoice'. The 'Flattened action: invoice' hint is cryptic and doesn't clarify whether the tool is for invoice specifically or all subscription reads. It does not distinguish from sibling tools like guru_subscriptions_get or guru_subscriptions_search, which already cover specific actions.

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 no explicit guidance on when to use this tool versus the many sibling tools. It lists actions and their required parameters, but does not explain which action to choose in which scenario, nor does it mention any exclusions or alternatives. For example, it doesn't say to use guru_subscriptions_search for search operations; instead it lists search as an internal action, implying this tool could replace the sibling, which is confusing.

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