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

Annotations already cover read-only/idempotent/non-destructive, but the description adds real value beyond them: it rejects incomplete or mode-incompatible inputs rather than guessing, Topaz pricing depends on exact source bytes and cannot start work, and the result is explicitly non-authorizing. Slight deduction for repeating the 'read-only/no-cost' point three times rather than adding new traits.

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?

Front-loaded with purpose and usage, and the Seedance/Topaz examples are concrete. But it sprawls into a long run of edge-case sentences and restates the read-only/no-spend constraint multiple times, so not every sentence earns its place.

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 high-complexity pricing tool with a large sibling set, it covers mode constraints, engine selection, reference-duration semantics, and the Topaz prerequisite. An output schema exists so return values need no explanation; the only notable omission is guidance on the 'values' payload shape.

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 25%, so the description must compensate, and it does for several params: reference_video_durations_seconds, reference_audio_durations_seconds, reference_image_count, source, and the reference_mode routing rule. However, the free-form nested 'values' object, 'family', and 'canvas_project_id' remain unexplained anywhere, leaving genuine gaps.

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 generation cost') plus scope ('hypothetical', 'without paying'), and explicitly differentiates from siblings: aimixer_options (default-mode price) and aimixer_quote/approval/submit (actual generation). An agent can route correctly without opening any 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?

Gives explicit when-to-use ('user asks how many coins a hypothetical generation will cost'), when-not ('NOT a paid quote', 'for actual generation use aimixer_quote/approval/submit'), and prerequisite ordering for Topaz (import media first, then pass the managed reference). Alternatives and exclusions are both named.

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