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

Annotations already declare this a safe, closed-world read, and the description adds real context on top: data provenance (CMS Federal IDR public use file, 2025 Q4, 532,542 disputes), the paywall/key requirement, the reduced free preview output, per-answer vintage and flags, and the explicit 'Data only: Tensorust does not file or represent' disclaimer. It also surfaces a time-sensitive caveat (IPRO and Network Medical Review decertified Nov 4 2026). Gaps remain around failure modes — e.g., what happens with an unrecognized payer domain or a code with zero determinations — but overall the behavioral disclosure is well above the annotation baseline.

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 purpose is front-loaded, but the body is a single dense run-on that packs outputs, pricing, decertification news, and a legal disclaimer into one breath, making the recommended offer band — arguably the headline output — hard to locate. Nearly every clause carries information, but the lack of structure (no sentences or grouping) costs readability.

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 must enumerate return values, and it does so thoroughly (cell determinations, win rate, winning-multiple quartiles, plan offer, losing median ask, default-decision share, median days, per-arbitrator loss rates with fees and certification status, top entities, offer band, and dollar figures with a QPA). For a tool of this complexity the main remaining gap is the absence of any statement about empty cells, unknown codes, or payer-name mismatch handling.

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 3 is the floor; the description earns above that by explaining what the parameters are for — QPA is in dollars and drives the band/expected-value output, payer may be an email domain as recorded or a common name, entity selects an arbitrator to evaluate, and preview truncates the answer to cell size and win rate. It adds intent and consequence rather than repeating the schema's own wording.

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+resource combination: it computes No Surprises Act IDR determination statistics (cell determinations, provider win rate, winning offer quartiles, recommended offer band) for a given CPT/HCPCS code, payer and state, and cites the regulation and dataset vintage. It is unambiguous what the tool returns. It does not, however, distinguish itself from sibling tools like idr_entity_pick or idr_scorecard, even though it overlaps with them by returning 'the top three entities to propose' and per-arbitrator loss rates.

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?

Usage conditions are implied rather than stated: the payer/state/code framing tells an agent this is a per-cell lookup, and the pricing gate (free under 50 determinations or with preview=true, otherwise an enterprise key) is spelled out. But there is no explicit 'use this instead of idr_entity_pick/idr_scorecard when…' routing, and no guidance on when a QPA should be supplied versus omitted beyond the fact that it enables dollar figures.

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