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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the description does not need to repeat that. The description adds 'leitura' (read) which aligns with annotations, and 'Bulk support: accepts ids' provides extra info about batch behavior not present in annotations. No contradiction.

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 but structurally messy. It packs a list of actions and parameters in a compressed format without clear headings or separation. The '[Flattened action: subscriptions]' note is cryptic and could be clearer. While it is not overly long, the lack of organization reduces comprehensibility.

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 9 optional parameters and multiple implied actions, the description is insufficient. It does not explain return values, how cursor pagination works, which combinations of parameters are valid, or how to choose among actions. With no output schema and no additional context, an agent cannot reliably invoke this tool for a specific need like 'get subscriptions for contact X'.

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 must compensate. It maps some parameters to actions (e.g., 'search (email, doc, name, created_at_ini/end, cursor)' and 'get (id)'), but it omits parameters like 'account' and does not explain how to select an action (since no action parameter exists). The bulk support via 'ids' is mentioned, but details on required fields per action are missing. The description adds some meaning but is incomplete against a 9-parameter 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 opens with 'Contatos/clientes no Guru (leitura)' which is a broad noun phrase rather than a specific verb+resource. It lists multiple actions (search, get, transactions, subscriptions, affiliations, etickets) but the tool name is 'guru_contacts_subscriptions', creating ambiguity about the primary purpose. The '[Flattened action: subscriptions]' note partially clarifies but does not fully disambiguate from sibling tools like guru_contacts_search or guru_subscriptions_get.

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 guidance on when to use this tool versus the many sibling tools that specialize in specific actions (e.g., guru_contacts_get, guru_contacts_search, guru_contacts_affiliations). The description does not mention alternatives or exclusions (e.g., 'use for subscriptions only' or 'prefer dedicated tools for other actions'). Context is unclear for an agent deciding which tool to call.

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