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

Annotations already declare readOnlyHint=true, and the description is consistent with that while adding real context: the call is free, prices come from the charging endpoint itself, some tools yield null cost_cents and require a second call, and song_analyze/music_video_director are free or 3¢. It stops short of covering edge cases such as error behavior for unknown tools or whether quotes expire, which keeps it off a 5.

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 the key fact (free, exact price, pass as confirm_cents) and organized into Args and Returns sections with no filler. The middle sentence about studio versus other gate steps is dense and slightly convoluted, but every clause carries operational 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?

Despite having no output schema, the description documents the return shape ({ok, tool, cost_cents, price_cents, confirm_cents, notes?}) and explains the meaning of each field's variability across tools. Combined with the argument exclusions and per-tool quirks, an agent has everything needed to invoke and interpret this tool correctly.

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 0%, so the description carries the full burden and does so: it enumerates the valid tool values, notes the special argument shapes (arguments.project_id for studio_render, arguments.plan for ai_short_create), and explains that arguments is the target tool's own arguments minus confirm_cents, idempotency_key, and quote_only.

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: it returns the exact price of a paid tool for given arguments, sourced from the same endpoint that will charge. It further distinguishes itself from the paid generation tools by naming which ones it covers and noting that any free tool answers 0, so an agent can tell what this tool is and is not for.

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 guidance: call it first, then pass the returned value as confirm_cents. It also gives per-target routing instructions (studio_render and ai_short_create return the server quote; studio_voice, studio_visual, studio_music, studio_create_from_audio return cost_cents null and should be called with confirm_cents: 0), which is actionable rather than implied.

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