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

Annotations only declare it a safe read; the description adds substantial behavior: results are grouped per payer and per billing class/methodology/setting and are never blended, hospitals are ordered most-hospitals-first, the exact summary statistics returned are enumerated, and a concrete failure mode (UNAVAILABLE) is disclosed. These are facts an agent cannot get from the annotations or schema.

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?

Two dense but well-ordered sentences: scope and grouping first, then return fields, then the chaining hint, then the failure condition. The compressed statistics list ('min/avg/median-of-hospital-averages/max') is terse rather than padded, and nothing reads as filler.

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 grouped read with no output schema, the description supplies return fields, grouping rules, ordering, chaining, and error behavior — enough to call it correctly. It is silent on result size or truncation/limits despite aggregating 'across hospitals', which is the one gap an agent might hit when a common code spans thousands of hospitals.

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?

With 67% schema coverage, the schema already documents filter semantics and code_type examples, so the description does not need to restate them. It does add real meaning by emphasizing that billing classes/methodologies/settings are never blended and that the summary is keyed on all three, which clarifies why the filter exists. No added detail on code formatting or how code_type interacts with filter.

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?

Names the resource precisely: negotiated payer rates for a given (code_type, code), one summary row per payer × billing class/methodology/setting, aggregated across hospitals with the listed statistics. It is distinguishable from siblings because it points at list_code_payer_hospitals as the drill-down. It loses a point only because it leads with a noun phrase rather than a verb, so the 'list/summarize' action is inferred.

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?

Gives explicit follow-up routing (use the returned payer_slug with list_code_payer_hospitals) and a prerequisite/failure condition (fails with UNAVAILABLE until the hospital-prices snapshot is open). It does not say when to prefer this over nearby siblings such as get_code_price_distribution or get_code_provider_terms_summary, so the alternative-selection guidance is incomplete.

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