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

Annotations only assert readOnlyHint=true, and the description meaningfully extends that: no charge occurs, parameters are validated, the exact cost is returned, and specific failure modes are surfaced (subscription required, model offline, concurrent job limit, invalid params, daily cap). This is substantive behavioral context beyond the safety hint.

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 sentences, zero filler, with the most decision-relevant fact (free, non-charging) front-loaded before the secondary benefit of rejection reporting.

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?

Given a nested params object whose schema lives in list_models and the absence of an output schema, the description does the important work of saying what comes back (exact credit cost plus rejection reasons). It does not describe the response shape in detail, a minor gap for an estimation tool.

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%, so model, mode, params, and version are already documented in the schema, including the pointer to list_models for mode-specific params. The description adds no parameter-level detail, so the baseline 3 applies.

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?

States a specific verb and resource (estimate credit cost) plus the crucial distinguishing trait: it is a free dry run that validates without charging. The added note about reporting rejection reasons separates it cleanly from siblings like generate_music and check_account.

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 'free dry run ... without charging' framing makes the intended pre-flight use clear, and listing rejection causes implies it precedes an actual generation. It never names generate_music as the alternative to run after a successful estimate, nor states when not to use it, so it stops short of explicit routing.

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