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

Annotations include readOnlyHint=true, idempotentHint=true, destructiveHint=false, which are consistent with the description's 'leitura' (reading). The description adds 'Bulk support: accepts ids for batched execution', which is a useful behavioral disclosure beyond annotations. However, it does not describe the return format or any error behavior. It also lists multiple actions (search, get, transactions, etc.) in the description, implying the tool can perform multiple operations, but the flattened action is transactions, so the description is ambiguous about what the tool actually does. Since annotations already establish safety (read-only, idempotent), the description's contribution is minimal and partially confusing.

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 cluttered list of actions and parameters, which is not concisely structured. It is front-loaded with 'Contatos/clientes no Guru (leitura)' but then dumps a list of actions with parameters in parentheses, which is hard to parse. The 'Flattened action: transactions' line is confusing because it suggests that despite listing multiple actions, the tool actually only does transactions. The bulk support note is a separate sentence. This structure does not help an agent quickly understand the tool's core purpose. It could be rewritten as a clear statement of the primary function with parameter details.

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 tool has no output schema, and given the complexity of transactions (likely returning transaction details), the description is incomplete. It does not describe what the tool returns when given an 'id' or 'ids'. It also fails to explain the relationship between the 'transactions' action and the other actions listed, which is confusing. The annotations provide safety but not operational detail. The description should clarify the input requirements and output expectations for the transaction action, especially since bulk support is mentioned.

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 burden. The description mentions parameters like 'search (email, doc, name, created_at_ini/end, cursor); get (id); transactions (id); subscriptions (id); affiliations (id); etickets (id)' and 'Bulk support: accepts ids for batched execution'. However, it does not explain the meaning of each parameter beyond listing them. For the flattened transaction action, it expects 'id' or 'ids', but the description does not clarify what each parameter represents (e.g., what does 'id' refer to? A contact ID? A transaction ID?). The description adds some value by specifying which parameters are used for which sub-action, but it fails to provide sufficient semantics for the core action 'transactions'.

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 is a list of actions the tool supports, with the primary action being 'transactions' (flattened action). It identifies a specific resource (contacts in Guru) and the main action is transactions, but it's cluttered with multiple other actions (search, get, subscriptions, etc.) that are likely separate tools in the sibling list (e.g., guru_contacts_search, guru_contacts_get). This muddies the purpose. The description does not clearly state that this tool exclusively handles transactions for a contact; it bundles multiple actions, making it unclear what distinguishes this tool from its siblings.

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 lists acceptable parameters for the flattened action (id, ids) and mentions bulk support, but it does not explicitly state when to use this tool versus alternatives like guru_contacts_search or guru_contacts_get. There is no mention of when not to use it or any alternatives. The presence of sibling tools like guru_contacts_get, guru_contacts_search, guru_contacts_affiliations, etc., suggests this tool is for a specific action, but the description fails to clarify which action is this tool's primary purpose and when to choose it over others.

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