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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description goes well past them: it names the upstream feed, the specific regions and source price lists, the monthly granularity and October 2020 floor, and — critically — that the price-per-GPU-hour figure is derived by dividing by the GPU count on the provider's spec page. It also guarantees no averaging across providers, which materially affects how the agent should interpret and present results.

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?

The first sentence front-loads the core definition and the source, and each subsequent clause carries real information (granularity, derived metric, filter axes). It is dense but not padded; the nested parentheticals in sentence one slightly slow parsing of the most important content.

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 present, the description usefully enumerates the returned fields — listed instance-hour price, derived GPU-hour price, each price change, and history — so an agent knows what comes back. The remaining gap is behavioural edge cases: what happens with no provider filter, and whether unlisted GPUs yield empty or all results.

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 100% and all six parameters are self-documenting, so the baseline of 3 applies. The description mostly restates the filter axes already in the schema and does not clarify the interaction between 'since'/'until' and 'history' (that the date window narrows the change history rather than the returned rows).

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 a specific resource — the published on-demand list price for renting a GPU instance — and its provenance (AWS Price List, Azure Retail Prices). It does not name any sibling tool, so the contrast with search_compute_contracts (negotiated/contract prices) has to be inferred from the word 'list' and 'never averaged'.

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?

The description gives the filtering axes ('filter by GPU, provider, instance or date range') but never says when to prefer this over search_compute_contracts or how it relates to compute_market_events. The coverage limits (us-east-1, eastus, monthly back to October 2020) implicitly define when the tool will return nothing useful, which is a partial substitute for explicit guidance.

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