delete_task

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds real value on top: the confirmation requirement, the expected-title guard against acting on a stale ID, and the disclosure that Google does not expose recurrence metadata so the tool cannot be scoped to a single instance. That recurrence limitation is exactly the kind of caveat an agent cannot infer from structured fields.

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?

Two tight paragraphs with the destructive action and its preconditions front-loaded. The recurrence paragraph is longer than strictly necessary and its 'do not promise that...' phrasing is agent-directed rather than tool-directed, but the information is not wasted.

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, open-world mutation with an output schema present, the description covers the safety prerequisites and a Google-side limitation. What remains unstated is the failure mode when expected_title does not match the stored title, and the pointer to get_task for retrieving the exact title.

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 coverage is only 50%, and the description compensates by documenting the two undescribed parameters: expected_title ('its exact current title') and confirm ('confirm=true'). It does not explain why the title must match (staleness protection) or how the caller should obtain the current title, so it falls just short of full compensation.

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?

States a specific verb and resource with a scope qualifier: 'Permanently delete a task'. The 'permanently' and 'after user confirmation' framing immediately separates it from reversible siblings such as complete_task or update_task.

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?

Explicitly names the alternative path — 'prefer completion when appropriate' — and states the precondition of obtaining user confirmation plus the exact current title. The qualifier 'when appropriate' is left slightly vague rather than spelling out the condition, which keeps it short of a 5.

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