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

Annotations already declare readOnly=true, destructive=false and idempotent=false, so the safety profile is covered; the description adds genuinely non-obvious context: the return shape (time/price points plus first, last, change, high, low), the per-call price ($0.01 via x402 USDC or card key), first 25 free, failed calls free, and the explicit warning that repeats are not free because each call is charged. That last point meaningfully explains the non-idempotent hint. It does not cover rate limits, point density/downsampling, or error behavior for a bad slug.

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 capability and the required inputs are front-loaded, with the example and pricing pushed to the back where they belong. There is some redundancy — "Price $0.01/call" is restated as "each call is charged, so repeats are not free," and "Reads or computes only and changes nothing" largely echoes readOnlyHint — but both restatements carry a practical instruction effect, so the waste is minor.

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 no output schema, the description correctly shoulders the burden of explaining return values, and it also covers the cost model, interval range and the slug-vs-token-id input fork. Missing pieces are edge-case behavior: what happens with an unknown slug, whether long intervals are downsampled, and any cap on returned points.

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% and it already documents slug/URL acceptance, outcome defaulting to the first outcome, the interval enum and its 1w default, and that token_id substitutes for slug. The description only adds a real example slug value and restates the slug-or-token-id choice, so it is a modest increment over the schema. Baseline 3 applies when the schema does the heavy lifting.

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 names a specific verb and resource ("Polymarket price history of one market outcome from the CLOB") and immediately scopes it to a single outcome's time-series, which cleanly separates it from sibling tools like polymarket_markets, polymarket_events and polymarket_orderbook (current book, not history). It also enumerates the returned aggregates (first, last, change, high, low), so an agent knows exactly what it gets without opening a schema.

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 concrete use cases — "chart how the odds moved, spot a swing after news, or backtest a signal" — which is a clear picture of when to reach for it, plus a worked example slug for the slug-based call path. It stops short of explicitly naming alternatives or exclusions (e.g., use polymarket_orderbook for live depth), so routing versus siblings is still inferred.

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