task_verify

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds real behavioral value the annotations cannot: it discloses the resulting state machine transitions and the maxRepairRounds exhaustion path, which is exactly the kind of side-effect an agent needs before calling a destructive tool.

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 sentences, front-loaded with the action and then the outcome semantics. Little waste, though the word 'durably' is vague and slightly redundant with 'apply the verdict'.

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, non-idempotent mutation with 8 parameters, 13% schema coverage, and no output schema, the description covers only the state-transition behavior. It leaves permissions/auth requirements, the meaning of most inputs, and failure/error handling entirely undocumented.

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 only 13% across 8 parameters, so the burden falls on the description — yet id, error, evidence, timeoutMs, resourceWaitMs, and continueOnFailure are never mentioned. The one term it cites (maxRepairRounds) is not even a parameter, so it cannot compensate for the coverage gap.

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 a specific verb+resource (run verification gates, apply verdict) and clarifies the outcome semantics. It does not, however, differentiate from siblings like task_update or task_reconcile, which also mutate task state, so an agent must infer which to use.

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?

It explains what happens after invocation (pass→succeeded, fail→repairing) but never says when to call this versus task_update, task_reconcile, or task_status. No prerequisites or exclusions are given.

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