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

Annotations already mark this as non-read-only (mutation), open world, not idempotent, not destructive. Description adds key behavioral context: payment via x402 ($0.02/call), file size and format limits (5 MB, PNG/JPEG/GIF/WebP), and that it's a 'fast vision model'. No contradiction with annotations, and the additional details help the agent understand the cost and input constraints.

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?

Description is a single, well-structured paragraph that front-loads the core purpose and progressively adds details (inputs, outputs, use cases, technical limits, cost). Every sentence serves a distinct informative purpose without redundancy or wordiness. It is concise yet comprehensive.

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?

The output schema exists, so return values are not required in description. The description covers input methods, output types, file constraints, use cases, and payment/auth. It lacks mention of error handling or rate limiting, but given the openWorldHint annotation, the unpredictable nature is implied. Overall, it provides sufficient context for an agent to decide when and how to invoke this tool.

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. The description goes beyond the schema by providing example input syntax ('{url}' or '{image_base64}') and a specific question example ('what error is on this screen?'), plus clarifies that the question parameter replaces the default full description. This adds practical guidance beyond the schema's brief definitions.

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?

Description starts with a clear verb-resource pair ('IMAGE DESCRIPTION (vision AI) — POST') and explicitly lists what the tool returns: detailed description, objects, text, colors, style, or answer to question. This distinguishes it from sibling tools like post_generate_image (image generation) and get_scrape (web scraping), making the purpose unmistakable.

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?

Description provides concrete use cases ('alt text, screenshot triage, image search and moderation') and mentions the cost and auth mechanism. While it doesn't explicitly state when not to use it, the sibling list includes no similar image analysis tools, so the usage context is implicitly clear. Could improve by contrasting with get_a11y_check or other potential alternatives.

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