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

Annotations already declare idempotent and non-destructive, and the description correctly reinforces idempotency by explaining duplicate inputs return an existing run. It adds genuinely new context beyond the annotations, namely the auth prerequisite and the integrity constraint that solver-supplied test outcomes are rejected. It does not describe queue latency or what happens on plan rejection.

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?

Three tight sentences, front-loaded with the action and scope, then the dedup behavior, then the prerequisite. No filler, and each sentence carries distinct information.

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?

Auth requirements and idempotency are well covered, and there is no output schema to explain. But for a two-parameter tool where one parameter is an opaque nested object, the total absence of any plan documentation makes the definition incomplete for correct invocation.

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% and the description never mentions either parameter. 'plan' is a free-form nested object with no shape, required keys, or validation rules documented anywhere, and 'artifact_id' is only obliquely alluded to via 'durably stored files'. An agent has no basis for constructing the plan payload.

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 ('Queue checks on exact durably stored files'), which separates it from read siblings like find_verification_checks and get_verification_run. However, 'checks' is left undefined and the relationship to validate_verification_plan is never stated, so the agent must infer the pipeline stage.

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 gives two useful operating conditions: it requires a verified website or wallet session, and it returns an existing run for identical inputs. But there is no explicit 'use this instead of X' guidance against the many verification siblings, so the agent cannot tell when to validate first or when to poll get_verification_run.

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