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

Annotations only declare readOnlyHint=true, so the TTL disclosure ('returns image_id valid 5 minutes') and the ephemeral-processing framing add real behavioral value — the agent learns the handle expires and must be used promptly. The 'no size limit here' note also flags a capacity difference from palette_extract. The upload is a transient store consistent with a no-persistent-side-effect read hint, though the description could have made that non-persistence explicit.

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?

Four short sentences, zero filler, front-loaded with what the tool does and its key constraint (TTL), then the chaining instruction and the size rule. Nothing repeats the schema verbatim.

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?

Output schema exists so return values needn't be explained, and the TTL is covered. But with zero required parameters, the agent must choose among image, source_url, and image_base64, and the description gives no guidance on that choice — only the schema's inline note about local files with no public URL partly fills it.

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 three input modes (file reference object, source_url, image_base64) are already documented, and an output schema covers the return. The description still adds selection meaning by tying the 50 KB threshold to this tool rather than to the extractors, which is beyond what the schema states.

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?

Specific verb+resource ('Upload an image to Colour Memory') plus the returned handle ('image_id valid 5 minutes'), and it explicitly routes to sibling tools palette_extract and extract_image_colours. An agent can distinguish this from image_palette/image_brief siblings without opening a schema.

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?

'Use for any image over 50 KB' gives a concrete selection threshold, and 'Pass image_id to palette_extract or extract_image_colours' names the downstream consumers. It stops short of stating the inverse case (small images → skip ingestion and call the extractors directly with image_base64), which would have made it a 5.

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