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

Annotations already declare destructiveHint=true, and the description reinforces with 'Permanently delete' and 'Irreversible', adding behavioral context beyond the boolean hint. It also discloses bulk execution capability, but does not detail authorization needs or side effects beyond deletion itself.

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 extremely concise—two short sentences that immediately convey the core action, irreversibility, and bulk support. No extraneous words; every sentence earns its place.

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 destructive tool with 5 parameters and no output schema, the description covers its destructive nature and bulk capability but lacks parameter-level guidance and does not describe return values or error behavior. It is adequate but leaves gaps that an agent must infer.

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 description coverage, the description must compensate, but it only mentions that 'patient_ids' and 'manipulado_ids' are accepted for batched execution. It does not explain the required single parameters ('patient_id', 'manipulado_id') or the optional 'account' parameter, leaving the agent to infer relationships and usage.

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 clearly states the verb ('permanently delete'), the resource ('a manipulado for a patient'), and its distinct role among siblings (only delete operation for manipulado). This specificity helps an agent differentiate it from list, get, write, and other manipulado 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 provides clear context: it's irreversible ('Permanently delete... Irreversible.') and mentions bulk support via array parameters. However, it does not explicitly state when not to use it (e.g., if soft-delete is preferred) or compare to other tools, but given no sibling delete tool, the guidance is sufficient.

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