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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description earns credit for going further: it discloses that only real dated observations are returned with no interpolation, that reference indices are anonymised third-party values without public source links, and critically that the free tier ignores requested dates and returns latest preview values. That tier behavior is a substantial disclosure not present in structured fields.

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?

Four sentences, front-loaded with the data description and tier gating last, so the ordering is sensible. However sentences like 'Archived pages are reconstructed, official offer versions are published history, and Azure effective dates remain separate' are cryptic and pack several unrelated facts without clear payoff.

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 7 mostly-undocumented parameters, the description should carry more weight. It covers data provenance and access tiering well but omits return shape, default date-range behavior, and the meaning of the basis filter, leaving gaps an agent would need to guess at.

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 description coverage is only 14% (just includeFractional), and the description does not compensate: it never explains the 'basis' enum values (list/spot/ask/reserved/reference), how from/to bound the results, or what limit defaults to. Only 'reference' is obliquely characterized; the other six parameters are left undocumented in both schema and description.

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 states what is returned: 'Real dated GPU price observations with source and evidence URLs for provider rates,' which combined with the title identifies this as GPU rental price history. It is clear but does not differentiate from siblings like gpu.board or gpu.changes, and the core purpose is buried under provenance caveats.

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?

There is no guidance on when to use this versus gpu.board, gpu.changes, or power.history. The only usage-adjacent statement is the tier note ('Pro unlocks history; free returns latest preview values regardless of requested dates'), which describes an access constraint rather than when to select this tool.

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