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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: delta entries are raw JSON strings with a serialized (not parsed) `data` field, the response is wrapped in a `meta` object carrying `delta_last_id`, affiliate 27 is excluded, and there is no automatic retry. Some trailing boilerplate ('No wagers, account changes or guarantee of returns') is generic noise.

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?

Purpose is front-loaded in the first clause and the return-format detail is useful, but the third paragraph is a run-on of loosely related disclaimers ('Read-only Product data or price calculation... No wagers, account changes or guarantee of returns') that dilute the message. Roughly a third of the text does not earn its place.

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 the description needn't explain returns, yet it usefully characterizes the delta payload shape and the meta cursor for the polling loop, plus metering/auth caveats. It stops short of describing pagination limits or how an empty delta should be interpreted beyond the generic 'never infer coverage' warning.

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 stated schema coverage is 0%, so the description is expected to carry the load; it clarifies the `last_id` cursor semantics and the `delta_last_id` round-trip, but says nothing about `sport_id` or `affiliate_ids` filtering. In practice the nested schema fields themselves are well documented (sentinel UUID, affiliate ID list, affiliate_ids=0 sentinel), which offsets the gap but does not let the description rise above baseline.

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 event changes') and scopes it to events changed since `last_id`, which distinguishes it from market-delta siblings like v2GetMarketsDelta by the word 'event'. However, it never names or contrasts with the nearest alternatives (v1GetDelta, v1GetDeltaV2, v2GetMarketsDelta), so an agent must infer the difference from names 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?

The description implies the polling workflow ('subsequent polling', 'initial fetch' via schema, 'no background polling or automatic retry') but never explicitly says when to choose this tool over v1GetDelta, v1GetDeltaV2, or v2GetMarketsDelta. Constraints about metered usage and account-dependent coverage are stated, but no when-not conditions or exclusions relative to siblings.

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