ufc_athlete_stats

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, covering the safety profile. The description adds crucial behavioral facts: the filter parameter returns 0 rows instead of an error (verified), sorting is confirmed to work, and data quirks are documented (e.g., the `takedown_acuracy` misspelling, percentages/rates as strings, `avg_fight_time` in seconds, and per-15-minute averaging convention). This goes far beyond the annotations and prevents misuse.

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 lengthy but well-structured into distinct segments: purpose/alternative, return payload, caveats, example, and auth. The inline return schema is dense but necessary since there is no output schema. Each sentence serves a purpose, and key warnings are front-loaded. It is not as short as the ideal TDQS 4.3 example, but the density is justified by the tool's complexity.

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 and the absence of an output schema, the description is remarkably complete. It specifies the full return structure with all attribute names, explains non-obvious unit conversions and string formatting, documents the filter failure mode, names the working alternative, and provides an example call. The auth requirement is also stated. This is more than sufficient for an agent to invoke the tool correctly.

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% and each parameter has a description, so the baseline is 3. The description adds value beyond the schema by providing a concrete example (`{"sort": "-sig_strikes_landed", "limit": 10}`), listing verified sort fields, and explaining that `sort` is how you build a leaderboard. This practical invocation guidance helps the agent select and construct parameters correctly.

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 "League-wide FightMetric statistics, sortable — the all-time leaderboards," which clearly identifies the resource as league-wide all-time stats. It lacks an explicit retrieval verb like "list" or "get," but the Returns block and the guidance to use ufc_athlete for a single fighter make the tool's purpose unambiguous. It also distinguishes from the sibling ufc_athlete by scope.

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 explicitly states when not to use this tool: "this collection cannot be filtered" and directs users to ufc_athlete for single-fighter stats, even noting that ufc_athlete resolves the same record through `include` and "DOES work." It also clarifies that sorting works, which is the intended leaderboard use case, and provides a concrete example.

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