vizcom_render_sketch

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

Annotations cover safety signals (readOnly=false, idempotent=false, openWorld=true), but the description adds information beyond them: this call consumes Vizcom credits (a real cost), it must not be retried, and the response carries a prompt id that must be saved. That is meaningful behavioral context an agent could not infer from annotations alone.

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?

Three short, front-loaded sentences with no filler words. The credit-cost and no-retry warnings appear before anything else, and 'save the returned prompt id' is a clear actionable instruction.

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 credit-consuming mutation with five undocumented parameters and no output schema, the description is under-specified. It partially covers the return value (the prompt id) but omits the file-format expectations, what drawingId must reference, and which sibling to call next (e.g., vizcom_status or vizcom_get_result) to retrieve the result.

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 0% across five parameters (file, drawingId, prompt, style, influence), and the description adds nothing: it never explains what 'file' should contain (path, URL, base64?), what drawingId must reference, what 'style' or 'influence' do, or the prompt length limits. The description does not compensate for the coverage gap.

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 verb and resource: 'Submit exactly one render.' An agent can tell this initiates a render job. It stops short of distinguishing itself from the sibling vizcom_render_pipeline, which also sounds like a render submission, so the purpose is clear but not fully differentiated.

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?

The description gives failure-handling guidance ('Never retries submission') and a single-shot constraint, but no when-to-use guidance relative to vizcom_render_pipeline, vizcom_generate_board, or the create/upload siblings. Nothing says what to do after a failure or when to prefer this tool.

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