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

With no annotations, the description carries the full burden. It helpfully discloses that prices are list prices and pins the pricing table version (2026-10-26), which signals staleness assumptions. However it does not state that results are estimates, whether unsupported models error out, or what currency/units apply.

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?

Two dense sentences with the primary action and scope front-loaded, followed by the version stamp. No filler.

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 6-parameter calculation tool with no output schema and thin schema descriptions, the description covers the conceptual outputs well but leaves the return shape, currency, and failure behavior unspecified. Adequate but with clear gaps.

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 only 17% (just static_tokens), so the description must compensate. It does partially: 'per month' implies requests_per_month, 'prompt caching' maps to static_tokens, and 'across models / cheaper sibling' hints at compare_to. But model string format, token units, and compare_to semantics remain undocumented.

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?

Uses a specific verb ('Price a workload at list prices across models') and enumerates the three outputs: per-request cost, per-month cost, and prompt-caching effect. It does not name any sibling tool, so differentiation from optimize_prompt_payload or audit_repo_token_waste is left to inference.

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 implies a cost-estimation scenario but never states when to use this versus the sibling tooling (e.g. optimize_prompt_payload or audit_repo_token_waste). No prerequisites, exclusions, or alternative routing are given.

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