Design an Image (logo, vector art, UI mockup, photo)

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

With no annotations, the description carries the full burden and does so richly: offline/no-network generation, PNG export contingent on rsvg-convert or ffmpeg, logo -reversed and -icon variants, quota consumption via the user's API key, budget guard with cost breakdown and halt behavior, and the return payload (paths, size, license).

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 a one-line purpose then tight bullets grouped by asset family, with cost/quota caveats placed next to the feature that triggers them. Dense but every clause carries operational information; only marginal trimming is possible.

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 a 6-parameter schema with no annotations and no output schema, the description covers the decision-critical facts: offline vs API path, placeholder-vs-real output, budget guard behavior, and what is returned. An agent has everything needed to call it correctly and set expectations.

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 baseline is 3, but the description adds real meaning beyond the schema: it names style-word categories (palette, logo layout, type voice, 'sharp' corners), gives subject examples per asset kind, and clarifies generative quota use and approveOverBudget consent. The schema even defers to the description for style semantics.

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 (generate/design) plus the resource (visual assets) and enumerates the exact asset kinds it produces: logo, vector-art, ui-mockup, cinematic-photo, texture. It maps cleanly onto the assetKind enum and cannot be confused with the audio siblings (generate_voiceover, generate_soundtrack, generate_sfx).

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?

Explicitly routes the agent: logos/vector/UI are produced offline and free, while photo/texture require generative:true, otherwise 'you get a clearly LABELLED placeholder, not a photo.' It also states the budget-guard halt condition and that approveOverBudget should be used 'only if the user agrees,' giving clear when/and-when-not guidance.

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