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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real behavioral context beyond them: the full-field return payload and the timezone caveat that the default Australia/Sydney may shift the race day for overseas meetings, which is a genuine correctness trap an agent would otherwise hit.

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?

Front-loaded with the purpose and return contents, then a compact Args block with no filler sentences. The Args list largely restates the schema keys, which is redundant in principle but justified here given 0% schema coverage; length is appropriate for a six-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?

An output schema exists so return values need not be detailed, and the description still summarizes them. Combined with the prerequisite call to get_meetings(), the timezone disambiguation, and complete parameter documentation, an agent has everything needed to invoke this correctly on the first try.

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 carries the entire burden and does so: formats (YYYY-MM-DD, IANA timezone), value ranges (race 1-20), enum-like choices (gallops/harness/greyhounds, country codes), defaults (gallops, au, Australia/Sydney), case-insensitivity for track, and worked examples. Every one of the six parameters is meaningfully specified.

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 and resource ('Get the full race form for a specific race') and immediately enumerates what comes back: runners with barriers, jockeys, trainers, form, and ratings. This distinguishes it cleanly from siblings like get_race_results (results, not pre-race form) and get_runner_profile (single runner, not the full field).

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?

Gives an explicit sequencing instruction: 'Use get_meetings() first to find available tracks for a date,' which names the sibling and the precondition. It does not, however, state when to prefer this over get_race_results or get_predictions for a given race, so the routing guidance is partial.

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