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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description goes beyond them with genuinely useful behavior: affiliate 27 is excluded, access/delay/metered usage depend on the connected account, results are bounded and cacheable by date, there is no automatic retry, and an empty result does not imply missing coverage. It does not describe pagination or the shape of a ranked outlier, but the additions are substantive.

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 core definition is front-loaded and the consensus sentence is excellent, but the tail accumulates boilerplate ('Read-only Product data or price calculation', 'No wagers, account changes or guarantee of returns') that reads like compliance copy rather than invocation guidance. Several sentences could be compressed without losing agent-relevant information.

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?

An output schema exists, so return values need not be explained, and the description covers the remaining gaps an agent would care about: read-only nature, account-dependent metering, bounded/cacheable scope, excluded affiliate, and empty-result interpretation. The one real omission is sibling differentiation, which matters given the near-duplicate outlier tool in the list.

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 property (date format, limit, min_peers as minimum peer prices for consensus, affiliate_ids format, affiliate 27 exclusion), so the structured field already carries the parameter burden regardless of the reported coverage figure. The description reinforces the consensus concept and the affiliate-27 exclusion but adds no format, default, or range detail the schema lacks.

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 and resource and then defines what an 'outlier' actually is: prices from one sportsbook most out of line with the peer-book consensus for a matching event/market/period/participant/line. That is far more informative than the tautological title. However, it never distinguishes itself from the near-identical sibling v2GetOutliersBySportAndDate, which is the single most important disambiguation an agent needs here.

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?

It gives operational context ('One bounded request, no background polling or automatic retry', 'Use returned canonical IDs') and warns not to infer coverage from an empty result, which is useful. But it offers no explicit when-to-use guidance and never names an alternative or the condition that would select v2GetOutliersBySportAndDate over this tool, so routing 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.