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

Annotations already carry the read-only safety profile, and the description adds genuinely useful behavioral context beyond them: prices are book-derived, expressed as 0..1 probabilities, and may differ from cached market-row data. It doesn't describe behavior for invalid or unknown token ids, but the core behavior is well disclosed. No contradiction with the annotations.

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?

Three sentences, front-loaded with the core action and batch constraint, followed by a targeted routing note. There is slight redundancy — 'live' appears in the title and twice in the description, and 'current best prices' overlaps with 'live book-derived prices' — but every sentence earns 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?

For a single-parameter, read-only batch fetch with no output schema, the description conveys the return semantics (book-derived 0..1 probabilities) and the freshness trade-off versus cached market rows. Minor gaps — the exact response mapping (tokenId → price) and error behavior for invalid ids — are low-stakes given the tool's simplicity and annotations.

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 coverage is 100% — tokenIds is documented as 'CLOB token ids' with minItems/maxItems constraints — so the baseline applies and the description need not duplicate it. It adds modest meaning by reframing them as 'outcome token ids' and mirroring the 50-item batch limit. This meets the baseline but adds little beyond the schema.

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 pair — batch-fetch current best prices for outcome token ids — with a concrete batch limit of 50. The contrast against the outcomePrices field on market rows differentiates it from market-retrieval siblings. The title reinforces the resource scope without ambiguity.

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?

Explicitly names the alternative (the outcomePrices field on market rows) and states the condition that selects this tool: when freshness matters, because cached market rows lag the book. It doesn't enumerate every price-related sibling (orderbook, price history), but the most likely confusion source is directly handled.

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