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

Annotations already declare readOnlyHint/idempotentHint and destructiveHint=false, so the description's added value is the cost and side-effect profile: 'Costs nothing, spends no credits, calls no provider' — a claim annotations cannot express. It also discloses that prompts are sent VERBATIM and that provider flags (--seed, --cf, --wm) survive, though it says nothing about authentication requirements (left to the schema) or the response shape.

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?

The core promise is front-loaded in the first sentence and every subsequent sentence carries distinct, load-bearing information (cost profile, model-class handling, list_models dependency). It is dense and packs three separate topics into one paragraph, which costs a little readability, but there is 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 12-parameter, 1-required tool with full schema coverage, the description covers the crucial unknowns: it is free, it creates nothing, it must be preceded by list_models, and some models take no prompt. With no output schema, it only implies what comes back ('the user sees the price') rather than describing the quote, which is the one remaining 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 description coverage is 100%, so the baseline is 3; the description earns above that by adding cross-parameter logic the schema does not — that `prompt` must be omitted entirely for list_models.prompt='none' models, and that the @name renumbering convention is handled server-side. It does not add per-parameter detail beyond that, so it stops short of 5.

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 precise verb+resource ('Price a render WITHOUT creating it') and immediately names the scope across media types (video, image, audio). It distinguishes itself from the render_* siblings by asserting the non-creating nature, so an agent can route between preview_render and render_video without opening either 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?

Explicit sequencing: 'Use this before any render_* tool so the user sees the price first', plus a prerequisite step ('Call list_models first and read `prompt` and `requires`'). It also gives a concrete exclusion case — prompt:'none' models (upscale, remove-bg, face-swap) must omit `prompt` and take source media instead.

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