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

Goes well beyond the annotations: fixed $0.02 price, USDC-on-Solana x402 payment handshake (call without payment to get the PaymentRequired challenge, retry with payment at _meta["x402/payment"]), an HTTP fallback URL, minimum-fact eligibility, refusal semantics, and the fact that verbatim steps and rank maps are returned so results are checkable. The non-readOnly annotation is explained by the billing side effect rather than contradicting the text.

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-loads purpose, then eligibility, then pricing/payment mechanics, which is the right order for a paid tool. Some phrasing is wasteful and opaque ('Fact bank TENDENCY', 'price RULED'), but the core content is tight.

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?

Payment flow, eligibility, refusal cases and output verifiability are all covered, so the paid-call mechanics are complete. However, for a 10-parameter tool with only 20% schema coverage and no output schema, the parameter surface and failure behavior (what a not_computable or insufficient-facts response looks like) remain under-described.

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?

Only hints at semantics for the (entity, status_field) pair and mentions a name-resolution alternative, but with 20% schema description coverage the other parameters (stream, league, team, position, series_id, limit, cursor) are left entirely undocumented. An agent gets no explanation of how name differs from entity_id, what a series_id means, or how limit/cursor paginate.

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 operation (computed direction over an (entity, status_field) fact history) and a concrete precondition (at least 3 facts), which an agent can distinguish from a plain status lookup. It does not explicitly contrast itself with fact_bank_status, so the sibling routing is only implicit via the named preflight.

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 a clear free-first path: call fact_bank_tendency_preflight to check eligibility before paying. It also names when the tool refuses (nominal, period-parameterised, structured fields -> not_computable), which is real when-not guidance. It stops short of saying when to prefer fact_bank_status instead of a tendency computation.

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