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

Annotations already establish readOnly and non-destructive, so the bar is lower, and the description still adds real behavior: result ordering, the distinction between NOT_FOUND (no payer rates at all) and an empty rates list (none for this code), and the dependency on an opened hospital-prices serving snapshot failing with UNAVAILABLE. What it does not cover is volume/pagination for hospitals with large plan lists, which matters for a per-plan expansion.

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 tight sentences; the resource definition and ordering come first, then revision semantics, then error states. No filler, though the trailing snapshot/UNAVAILABLE sentence is packed densely enough to read as an afterthought rather than a caller-facing prerequisite.

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 usefully sketches the return shape (rates with price terms, sorted) and covers both failure modes and the prerequisite snapshot state. For a 5-parameter tool with a nested filter object, the main gap is that filter behavior and result volume are left entirely to the schema.

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 80%, so the schema already documents hospital_id, code_type, and revision_id, and the nested filter object carries its own detailed description. The description adds only the intent behind revision_id (answering for a past filing) and the pairing of code_type with code; it says nothing about the filter parameter or how filtering interacts with 'every plan rate'. Baseline 3 is appropriate.

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 resource and scope: every per-payer, per-plan rate one hospital files for a given (code_type, code), plus ordering (cheapest average first) and price terms. That is far more than a restatement of the name. It stops short of explicitly naming a sibling to contrast with (e.g. get_hospital_provider_code_costs or list_hospital_code_costs), so an agent must infer the boundary from the resource wording alone.

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 one concrete usage rule: pass revision_id to answer for a past filing, which is genuinely actionable context. However, it offers no guidance on when to prefer this tool over the many sibling rate/cost tools, and no when-not conditions or prerequisites beyond the snapshot note.

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