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

readOnlyHint=true already tells the agent this is a safe, side-effect-free read, so the description's burden is lighter. It usefully implies the estimate applies to *planned* (not executed) calls, but says nothing about estimate accuracy, expiry, or what the response contains. Adequate with annotations carrying the safety profile.

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 short sentences, zero filler, with the core purpose front-loaded and the trigger condition second. Nothing could be removed without losing information.

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 batching tool over a 15-value type enum with nested params and no output schema, the description never indicates what the returned estimate looks like (per-item vs. total, currency, units). The readOnly annotation covers safety, but the return-value and input-shaping context are thin.

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 0% and the single `items` parameter is undocumented in the description beyond the phrase 'one or more planned create_* calls', which hints at batching but not the per-item structure. Nothing explains quantity limits, model_id, or how the 15 enum types map to cost models, so the description does not compensate for the coverage gap.

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 (estimate) and resource (token cost) with scope ('one or more planned create_* calls'), which cleanly distinguishes it from every sibling that actually creates or fetches assets. An agent can tell immediately that this computes cost rather than producing media.

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 trigger is explicit: 'Use when the user asks "how much".' There are no competing cost-estimation siblings, so no exclusions are needed. It stops short of stating prerequisites, such as whether the params must mirror the intended create call exactly.

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