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

Beyond the readOnly/destructive annotations, it discloses pagination behavior (default and 500 cap on page_size), that total_count is returned, that results are rolled up across the payer's plans, and critically the failure mode: UNAVAILABLE until the server has opened a hospital-prices snapshot. That dependency is exactly the kind of operational context annotations cannot carry.

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 sentences, front-loaded with the row-grain definition, then the use case, then operational constraints; nothing is padding. The compression is occasionally cryptic ("rolled up across the payer's plans there"), which costs a point but not clarity of intent.

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 7-parameter, nested-filter tool with no output schema, the description covers grain, pagination, ordering, snapshot dependency, and the prerequisite sibling call. What it omits is the shape of the returned rows (which fields a rate row contains), leaving the agent to infer the payload from the tool name and order_by enum.

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 71%, so the schema already documents code_type, payer_slug, page_token and the filter/order_by semantics. The description still adds value the schema lacks: the 500 page_size default/cap and the fact that rows are grouped before filtering. It does not elaborate on page_size's lower bound or the meaning of the order_by values beyond the schema's own default note.

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 first sentence names a specific verb (list rates), a precise resource (one payer's rate for a code_type/code at each hospital), and the exact row grain (one row per hospital and billing class/methodology/setting), plus the roll-up rule across plans. This clearly separates it from siblings like get_hospital_code_payer_rates (single hospital) and list_code_provider_hospitals (provider rather than payer view).

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 a concrete use case ("which hospital is cheapest for Aetna members") and points to list_code_payers as the source of payer_slug, which tells the agent the prerequisite call ordering. It stops short of naming the closest alternatives (e.g. get_hospital_code_payer_rates) or stating when not to use this tool.

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