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

Annotations provide readOnlyHint=true, and the description adds meaningful behavioral context: it inverts de-vigged 1x2 and totals prices, uses a bivariate-Poisson (Dixon-Coles) model, returns top-K scorelines, fitted goal rates, probability mass coverage, and an 'ah_ev_check' consistency metric. It also clarifies that the asian-handicap fair price is held out of the fit. This goes beyond the annotation by explaining the internal methodology and output semantics. It doesn't mention rate limits or error behavior, but for a read-only analytical tool this is strong.

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 well-structured with a clear first sentence, a detailed methodology paragraph, and a compact Args list. It front-loads the core purpose and scope. It is somewhat long, but every sentence adds value—methodology, output contents, consistency check, and exclusions. The Args section is redundant with the schema but serves as a quick-reference, so it earns a 4 rather than a 5.

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 (bivariate-Poisson inversion, multiple outputs, consistency metric), the description covers the key aspects: input format, supported sport, output contents, and the meaning of the consistency check. There is no output schema, so the description's explanation of return values is essential and mostly sufficient. It doesn't specify error cases (e.g., what happens if the fixture isn't found or if markets are missing), but for a read-only analytical tool this is a minor gap.

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 full burden. It explains 'query' as a natural-language fixture with examples, 'sport' as an optional filter limited to 'football', 'date' as a UTC disambiguator, and 'top' as the number of scorelines (default 5, max 10). This adds meaning beyond the raw schema, which only shows types and defaults. It doesn't detail the exact format of 'date' beyond 'YYYY-MM-DD' (which it does), so a 4 is appropriate.

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 states a specific verb ('inverts... into a bivariate-Poisson score grid'), a clear resource (market-implied correct-score probabilities for one football match), and explicitly distinguishes itself from InferSports predictions. It also names the scope constraint ('Football only, one match per call'), which separates it from sibling tools like compare_prob or get_match_odds.

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 clearly states when to use this tool: for market-implied correct-score probabilities for a single football match. It explicitly says 'never an InferSports prediction' and 'Football only, one match per call,' which helps an agent avoid misuse. However, it doesn't explicitly name sibling alternatives or state when NOT to use it in favor of another tool, so it falls slightly short of a 5.

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