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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, yet the description adds real operational context beyond them: the delta_last_id bootstrap is only safe when X-Data-Delay-Seconds: 0, one bounded request with no polling/retry, metered usage follows the account, affiliate 27 excluded, and an empty result must not be read as absent coverage. That is substantive disclosure, though it is delivered as an undifferentiated run-on rather than organized caveats.

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 opening sentence restates the title almost verbatim ('Get events with markets for a sport and date Returns events with full market/odds data...'), wasting the most valuable position. The remaining content is a dense concatenation of unrelated caveats (main lines, delta bootstrap, rate/usage, affiliate exclusion, wagering disclaimer) with no ordering or formatting, making it hard to scan for the decision-relevant facts.

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?

With an output schema present, return-value explanation is unnecessary, and the description covers the important call-time caveats: date-boundary handling is in the schema, delta bootstrapping conditions, no-retry expectation, and the empty-result warning. The main gap is sibling disambiguation, which for a tool in a family of ~70 near-duplicate endpoints is a meaningful omission.

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 schema itself documents every query parameter in depth (sportID enum values, offset semantics, market_ids limits, affiliate_ids sentinel behavior), so the schema carries the parameter burden. The description adds only one nuance beyond it, that main_line=true also excludes closed prices, which is a modest but genuine addition; nothing else about the two top-level parameters is clarified.

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 events with markets for a sport and date') and the scope (full market/odds data for one sport+date). It is clear on its own, but it never distinguishes itself from near-identical siblings such as v1GetEventsBySportAndDate, v2GetEventsByDate, or v2GetMarketsBySportAndDate, so an agent cannot tell which one to pick from the description alone.

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?

Offers some routing guidance: 'This is the primary endpoint for building odds screens' and a conditional alternative ('use scoped snapshots instead') for the delta-bootstrap case. However, there is no guidance on when to prefer this over the v1 equivalent, v2GetMarketsBySportAndDate, or the openers/closing siblings, so the sibling selection burden is left to inference.

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