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

Annotations already establish read-only, closed-world, non-idempotent behavior, so the bar is lower. Beyond that, the description adds real behavioral value: results are ordered 'latest first' and it discloses the exact returned fields and derived aggregates (wins, top-three, strike rate). It does not describe failure modes for an unknown id, keeping it at 4.

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, front-loaded sentence that leads with the core purpose ('Last runs of a horse, jockey or trainer') before enumerating fields. The dense field list is justified because no output schema exists to carry that information, though it slightly strains readability.

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?

With no output schema, the description correctly assumes the burden of describing return values, and it does so thoroughly (fields plus aggregate stats). Combined with read-only annotations and a fully covered input schema, an agent has nearly everything needed; only edge-case behavior (unknown id, empty history) is unaddressed.

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 100%, so all three parameters are already documented, making 3 the baseline. The description reinforces the entity kinds (horse, jockey, trainer) that map to 'kind' and implies the run history governed by 'limit', but adds no format or syntax detail beyond the schema.

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+resource: it retrieves the last runs (form) of a horse, jockey or trainer, and even enumerates the returned fields. This clearly separates it from the find_* siblings, which locate entities rather than return their history. It stops short of explicitly naming a sibling alternative, so 4 rather than 5.

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?

Usage is only implied: the description makes clear this returns recent form, but never states when to reach for it versus e.g. get_race or find_horses. The schema's mention of find_horses as an id source hints at the workflow but the description itself gives no when-to-use or exclusion guidance.

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