get_race_predictions

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behaviour: an all-or-nothing parameter contract that throws on partial input, and a hard 366-day cap on the ranged branch. It does not describe the returned payload, but the error and limit disclosures are the higher-value additions.

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?

A single dense sentence with the two branches front-loaded and no filler. The endpoint-path notation ('.../latest/{displayName}') is slightly cryptic and internal-facing, costing it a point, but nothing is wasted and the constraint (366-day cap) lands at the end where it is needed.

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?

Invocation is fully covered, including the failure mode and range cap, and the readOnly annotation covers side effects. However, with no output schema, the description says nothing about what a prediction response contains or how many race distances it covers, leaving the agent to guess at the shape of the result.

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?

The schema expresses no dependency between the three parameters (required is empty), so the description's all-or-nothing rule is information the schema cannot convey. It also clarifies that no-params and all-params are the only two legal states. With 67% schema coverage on the date fields and enum already documenting 'type', this compensates well.

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 never plainly states that the tool returns race predictions; it only describes the two request branches and the URL shapes each one hits. The verb ('hits') and resource are implied rather than named, so an agent must lean on the tool name to infer the actual purpose. It is behaviourally specific but purpose-vague, and it differentiates itself from siblings only by implication.

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 a clear operational fork: omit all params to get the latest prediction, or supply all three to get a ranged result, and it warns that a partial combination throws. That is real when-to-use guidance. It stops short of naming any alternative sibling or stating a preference between the two modes beyond the parameter rule.

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