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

Annotations only supply readOnly/idempotent/destructive hints, so the description carries real weight and does: one paid GPT Image 2.5 generation capped at 5/day, existing artwork preserved until replacement succeeds, and default-deny capability semantics. It does not say what a draft save returns or what state changes when publish=true fires.

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 dense sentences, each carrying distinct information, with the core purpose front-loaded and the costly/hazardous behaviors called out early. Slightly packed but no filler sentences.

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 20-parameter mutation tool with no output schema and no annotations beyond hints, the description covers the key decisions but leaves the return shape unexplained and does not individuate most of the permission flags. An agent could call it, but not fully predict the result or the effect of the many allow* combinations.

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?

At 20% schema coverage the description must compensate, and it does for the highest-risk params: it explains subjectKind's account/strategy semantics, the regenerateHeroImage cost and rate limit, the explicit removeHeroImage conflict, and that omitted allow* flags default to deny. The many view-permission booleans, tags, title, and description still get no explanation beyond the default-deny generalization.

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?

"Creates or updates a draft for exactly one explicit subject" is a specific verb+resource with an explicit cardinality constraint, and the account-vs-strategy paragraph pins down what each subject kind produces. It does not name or differentiate against near siblings like publish_to_marketplace or upload_marketplace_publication_image, so it stops short of a 5.

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?

"then optionally publish" and the regenerateHeroImage=True wording imply when to use the tool, but there is no explicit when-not guidance and no routing to alternatives such as publish_to_marketplace, unpublish_from_marketplace, or get_my_marketplace_publication. Usage is inferable rather than stated.

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