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

The description claims the tool supports a 'check_in' action (code, status de check-in), which implies a state-changing operation consistent with write behavior". However, annotations explicitly declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. This is a clear contradiction. Additionally, the description only repeats 'leitura' (read) without disclosing any other behavior beyond what annotations already state.

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 short, but it's organized as a list of actions with a confusing '[Flattened action: get]' note. It front-loads the read-only nature but then introduces actions that may not apply, damaging clarity. It could be much simpler: state the tool gets an e-ticket by code.

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?

With no output schema and zero parameter descriptions, the description fails to explain what the tool returns, how 'account' parameter is used, or how this relates to other e-ticket operations. The mention of list/check_in without mapping to actual parameters (cursor, code) is incomplete. There is insufficient context for the agent to use this reliably.

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 three parameters (code, cursor, account) with zero descriptions. The description mentions 'cursor' for list and 'code' for get, but does not explain the 'account' parameter or clarify that only 'code' applies to the get action. There is no added meaning for any parameter, so agents must guess how to use them.

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 'Ingressos (e-tickets) no Guru (leitura)' and lists actions 'list (cursor); check_in (code, status de check-in); get (code)' but then declares '[Flattened action: get]'. This is confusing: it suggests the tool can perform multiple actions, including a mutating check-in, yet the tool is named get and the flattened action is get. It does not clearly specify that this tool only retrieves a single e-ticket by code, which is what would differentiate it from sibling tools.

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 gives no guidance on when to use this tool versus the sibling tools like guru_etickets_check_in or guru_etickets_list. In fact, listing check_in as an action could mislead the agent into thinking this tool handles check-ins, whereas a dedicated sibling exists. There is no direction on parameter selection or use context.

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