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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false). The description adds genuinely useful behavior beyond that: the prediction is 'scored only after reviewed resolution', it requires authentication, and it needs explicit operator approval (which aligns with the operatorApproved const-true parameter). This is meaningful disclosure the annotations do not carry.

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 short sentences with the action and timing front-loaded and no filler. Efficient overall, though the opening clause is slightly cryptic rather than crisp.

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 4-required-parameter write tool with full schema coverage and no output schema, the description covers the essentials: it is a mutation, it is scored later after review, and it requires auth plus operator approval. Only the read counterpart and pagination/return behavior go unmentioned, which is acceptable here.

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 100%, so the schema already documents claimId, probability, idempotencyKey, and operatorApproved, establishing a baseline of 3. The description adds little beyond what the schema says and its 'one probability per known operator' phrasing is mildly at odds with a single probability parameter, adding no useful semantic 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 gives a specific action (record one probability) and a timing scope (before any check is submitted), and the title 'Freeze a reproduction forecast' reinforces that this is a write-side forecast action distinct from the read-side morrowkin_get_claim_predictions. However, the phrase 'one probability per known operator' is awkward and does not name the claim resource directly, so the agent must combine name and title to be sure of the target.

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 supplies a real ordering constraint ('before any check is submitted'), which implies when to call it. But it never names an alternative such as morrowkin_get_claim_predictions for reading forecasts or morrowkin_submit_reproduction, and it gives no explicit when-not-to-use guidance, leaving routing to inference.

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