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

Annotations already declare mutation (readOnly=false), idempotency, and non-destructiveness. The description adds genuine behavioral detail beyond them: resume 'never repeats an uncertain model call' and 'rejects changed owner direction,' which concretely explains the idempotency guarantee. It does not explain what cancel does to an in-flight result, but the resume semantics are substantive.

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 sentences, front-loaded with the operation list followed by the resume safety guarantee. No filler, though jargon like 'unconfirmed dispatch by its existing identity' slightly obscures meaning for an agent unfamiliar with the domain.

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?

An output schema exists so return values need not be covered, and annotations carry the safety profile. Still, the prose-to-enum mismatch and total absence of parameter guidance leave the agent on a 3-required-parameter mutation tool with clear gaps before it can invoke correctly.

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%, so the description must carry parameter meaning and largely does not. It never names jobId, action, or workspaceId, nor explains the resume/cancel mapping to the action enum; only the vague phrase 'by its existing identity' hints at the identifier parameter without any format or usage detail.

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 names specific operations (cancel a queued/running analysis, recover an unconfirmed dispatch, deliver a retained result) for the 'learning job' resource, so the general purpose is clear. However, it lists three operations while the action enum only offers 'resume' and 'cancel', leaving the agent unsure whether 'recover' and 'deliver' are separate actions or aliases of resume. Sibling differentiation from learning_get/learning_start/learning_quote is absent.

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?

Provides implied context: cancel applies to a queued or running analysis, and resume is a safety operation that 'rejects changed owner direction.' There is no explicit when-to-use-vs-alternatives guidance (e.g., vs learning_get for status, or vs generation_jobs_cancel), so routing between siblings is left to inference.

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