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

Adds substantial context beyond the annotations: latency (10-30s), cost (one monthly image credit) and that balance is returned, channel-specific return handling (s3_key over MCP, attachment over SMS/WhatsApp), and persistence to the media library. This is exactly the behavioral detail annotations don't convey.

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-loads the purpose and the key style instruction, then packs cost, return, and alternative into dense but earning sentences. Slightly long, but nearly every clause carries actionable 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 no output schema, the description fully explains what is returned on each channel and how to use it downstream (images field of draft tools), plus cost, timing, and persistence. Nothing needed to call it correctly is missing.

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 the baseline is 3. The description adds genuine semantic guidance beyond the schema for the prompt ('Describe the picture, not the post') and the do-not-restate-style rule, which shapes how the required parameter should be filled.

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 an original image with AI') and its purpose ('to accompany a post'), and explicitly differentiates from the sibling upload_image. An agent can distinguish it instantly.

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 ('accompany a post'), a key instruction ('do NOT restate colours or visual style'), and names the alternative with its selecting condition ('Use upload_image instead when the user already has a picture').

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