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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds behavior annotations don't: the ranking (cheapest first), the currency (USD), the unit semantics per kind, and the per-row fields card_url and cite. It doesn't mention pagination or what happens when limit exceeds available rows, but the core behavioral profile is well disclosed.

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 core promise front-loaded and the exclusion and row fields trailing. The kind/unit mapping is compressed into a readable parenthetical. It borders on crammed but every clause carries 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 three-parameter read-only lookup with no output schema, the description covers what's returned (cheapest offer per model, card_url, cite) and how rows are ordered. It omits limit/pagination behavior, which is the only meaningful gap.

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 schema already documents kind, limit, and quantity, including defaults and enum meanings. The description restates the per-kind quantity units (images, seconds, characters, minutes), which reinforces but does not materially extend the schema. Baseline 3 is appropriate.

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 (per-unit media job cost) and a precise scope: models that sell image/video/voice by their own unit, cheapest offer per model, ordered cheapest-first, in USD. It explicitly excludes token-priced models, which separates it from estimate_cost without opening a schema.

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?

It gives a concrete exclusion and names the alternative: 'Models priced per token are not in it (use estimate_cost)'. That's a real when-not-to-use rule. It doesn't distinguish itself from closer siblings like cheapest_offers or cheapest_models_by_task, so the routing guidance is clear but incomplete.

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