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

Goes well beyond the readOnly/destructive annotations: it discloses that fee_rate is read live from Polymarket's GET /fee-rate per token_id and never hardcoded, that maker fees are zero across categories, and that settlement is in USDC on Base. These are exactly the operational traits an agent needs that the annotations cannot convey.

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 fee-source disclaimer and the formula are front-loaded, and each sentence carries content (formula, live-rate sourcing, maker exclusion, price fallback, id resolution, denomination). It is dense but not padded; slightly more compact than ideal but no filler sentences.

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 described, and annotations already carry the safety profile. Given a read-only 6-param estimator, the description supplies everything else — formula, data source, fallback behavior, id resolution path, and currency — so nothing essential is missing.

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%, so the baseline is 3, but the description adds real meaning: price-omission falls back to the live best book quote for side, and token_id can be supplied raw or resolved from market_slug + outcome. Those are behavioral semantics coordinating multiple parameters, above what the schema states individually.

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 (estimate) plus the exact resource (Polymarket's taker fee) and immediately scopes it against adjacent concepts — gas, slippage, and AlphaPipeline's own charge. An agent can tell precisely what quantity this returns without opening the 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?

The 'NOT gas, slippage, or AlphaPipeline's own charge' clause and the 'makers pay 0, taker only' note clarify what the tool computes and excludes, which is useful disambiguation. However, it never routes the agent to a specific sibling (e.g. prediction.exit_capacity_audit or prediction.polymarket_mispricing) or states when this estimate is the right one to call, so usage is implied rather than prescribed.

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