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

Annotations already establish readOnly/openWorld=false/destructive=false, and the description layers on substantial behavior the agent could not otherwise know: the 3-provider minimum and 3-MAD filter that gate publication, which fields appear for published vs. unpublished families (status + providers only), and the exact not_found error payload with a models list. That is well beyond 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?

Front-loaded with the purpose and the call decision, then the family taxonomy, then the publication rule and error shape — a sensible information hierarchy. It is dense but nearly every clause carries operational meaning; the id-format sentence is the most expendable piece.

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 and no annotations about return shape, the description fully carries that burden: it enumerates median/p25/p75/providers for published families, status/providers for suppressed ones, and the error contract. Nothing an agent needs to interpret a response 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 both parameters are already documented, and the description's 'Omit model for every model' largely restates the schema's 'Empty returns every model'. It adds no new detail on response_format, so this sits at the baseline where the schema does the work.

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 gives a specific verb and resource ('Latest GPU rental price index families, in US dollars per GPU-hour') and the body defines exactly what a family is (model x segment x class, id IG.<GPU>.<SEGMENT>.<CLASS>). It differentiates itself from aggregation-oriented siblings only implicitly, via 'Segments are never combined, and no cross-segment figure is returned', rather than naming market_totals as the alternative.

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?

'Call this for the current index level of a GPU model in one market segment' plus 'Omit model for every model. Pass one model name for that model only' gives clear selection logic for the model parameter. It stops short of explicit exclusions (e.g., when to prefer market_totals or compute_vaults instead), so the when-not guidance is inferred rather than stated.

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