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

readOnlyHint=true already covers the safety profile, and the description adds genuinely useful behavior: results are ordered cheapest first, priced in USD, cover every current provider of the model, and account for input, output, cached input tokens and request counts. It does not describe failure behavior (e.g. unknown model names) or result shape in detail, keeping it below 5.

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?

One compact sentence front-loads the outcome (cost of a workload) before qualifying scope and ordering. The trailing gloss '- what the same job costs where' is a redundant flourish that adds no information but is small enough not to be distracting.

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 carries the burden of telling the agent what comes back, and it does: per-provider USD costs sorted cheapest first. For a five-parameter, read-only pricing query this is nearly sufficient; only error/edge-case behavior for ambiguous model names is left unaddressed.

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 the baseline of 3 applies; the description's parenthetical restates the workload components (input, output, cached input tokens, requests) but adds no units or semantics beyond what the individual property descriptions already provide. It does clarify that all four are components of a single job rather than independent filters.

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 (cost of a workload for one model across every current provider, in USD, cheapest first) and the scope of the computation is unambiguous. The verb is carried only by the tool name 'estimate_cost' rather than the sentence, and no sibling tool is named for contrast, so it stops short of 5.

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?

Usage is implied rather than stated: 'at every current provider of one model' suggests the cross-provider, single-model scenario, which implicitly distinguishes it from compare_models, but the description never says when to prefer this over cheapest_for_workload or get_model_prices. No explicit when-not conditions are given.

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