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

With no annotations present, the description carries the full burden of behavioral disclosure. It explicitly states 'All endpoints require x402 payment (USDC on B...' and lists per-endpoint costs, which is crucial for an AI agent deciding to invoke the tool. It also discloses data provenance ('derived from 7-day precipitation data') and coverage ('35 racecourses'). It does not mention failure modes or rate limits, but the payment and scope disclosures are substantial.

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?

The description is long (~600 words) but is efficiently organized as a bulleted list of endpoints, each with a one-line explanation. It front-loads the summary and then provides scannable detail. The opening sentence is slightly redundant with the later endpoint list, and the size is at the upper limit, but every line adds value for a 13-action, 20-parameter tool.

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?

Given the tool's complexity (13 endpoint actions, 20 parameters, no output schema), the description is remarkably complete. It explains every action's purpose, key inputs (via examples like 'Cheltenham Gold Cup' in schema), pricing, coverage, and payment requirements. The per-endpoint summaries effectively act as output descriptions, making the tool self-explanatory for selection and 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?

The input schema already has 100% description coverage, but many descriptions are terse (e.g., 'date', 'mode', 'regions'). The tool description compensates by giving detailed semantic meaning to the 'action' parameter's enum values, which is the core selector. It does not elaborate on the other parameters, but the schema's decent coverage plus the explanation of action values raises it above baseline.

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 opens with a clear summary ('Global horse racing intelligence') and then enumerates 13 distinct actions, each with a specific verb and resource: 'scanner — Arbitrage scanner — scan all active racing sports for guaranteed-profit opportunities', 'card — Race card — complete meeting briefing'. This unambiguously distinguishes the tool's sub-operations from each other and from sibling tools.

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?

The description effectively provides internal usage guidance by detailing what each endpoint does, e.g., 'form — Form guide — deep horse form analysis', 'going — Going conditions — live ground conditions'. It also notes payment requirements, implying it should be used when the agent can handle blockchain payments. However, it doesn't explicitly contrast with sibling tools or state exclusions, so it's clear but not fully explicit on alternatives.

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