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

Annotations cover only the safety profile (readOnly/openWorld/non-destructive), and the description adds substantial behaviour beyond that: the default summary bounds arrays while preserving counts, hasObservedPrice:false vs omitted vs unknown, sourceObservation:null meaning 'unavailable provenance, not proof of absence', priceBasis:'unquoted' meaning never traded with no usable book, and the referenceProbability composition (liquidity-weighted median over matched real-money venues with venueCount and spreadPoints, which must be quoted together). It also discloses auth ('No API key required') and data-capture windows (volume points since 2026-07-02).

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-loaded with purpose and payload, and most parentheticals carry real semantic load. It is nonetheless a very long, heavily nested single block, and the caveat chain (hasObservedPrice / sourceObservation / priceBasis) is dense enough that a reader can lose the main thread before reaching the pm_quote routing line.

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, annotations covering safety, and 100% parameter coverage, the description supplies exactly the missing layer: field-level semantics for the ambiguous/auxiliary fields, default-vs-full behaviour, and the sibling routing rule. Nothing an agent needs to call or interpret the result correctly is absent.

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 100%, so the baseline is 3. The description goes modestly beyond it by explaining what detail=full actually yields versus the bounded default summary, and by framing source as the venue key for slug resolution, but fiat is left entirely to the schema and no format/syntax detail is added.

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+resource+keying scheme: fetch free public detail for one prediction-market event by venue + slug, then enumerates the concrete return payload (outcomes/probabilities, price snapshots, resolution evidence, crossSourceMatches, referenceProbability, whales, related events/news, volumeHistory). It explicitly separates itself from the tradability sibling: 'This is the cross-venue research view; for tradability use pm_quote.' An agent can place it against pm_data_events/pm_quote without opening schemas.

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?

Clear usage context and one explicit alternative ('for tradability use pm_quote', plus 'No API key required'), and it gives a condition for the detail flag ('Set detail=full only when the untouched provider-rich record is needed'). It does not, however, disambiguate against the closest research siblings (pm_data_canonical, pm_data_disagreements, pm_data_events) even though it describes canonical/cross-venue concepts those tools likely own.

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