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

Annotations already declare non-read-only, non-destructive, non-idempotent and open-world. The description goes beyond them by disclosing that publication takes effect immediately and that the listing carries a public 'Listed via AI agent' label — non-obvious, agent-relevant side effects. It stops short of saying whether a published listing can be edited or removed afterwards.

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 sentences, front-loaded with the effect of the call, then the public label, then the prerequisite. Nothing is redundant or padded.

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?

No output schema, so the description should cover more of the call's reality. It never mentions that credentials (agent_key, or legacy hostname/publish_key) or seller_role exist, even though only 'listing' is in the required set — an agent could reasonably attempt publication without auth. For a public-facing mutation with a deeply nested payload, that is a notable gap.

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 67% and the single required parameter is a nested object of ~15 fields with two large enums, so the schema largely carries semantics. The description adds only the indirect hint to fetch get_listing_schema first, which helps an agent construct the payload but explains no individual field meanings.

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 and resource: 'Publish a listing', plus the immediate effect ('Goes live immediately'). It doesn't differentiate from siblings such as create_buyer_request or the get_listing tools, but a read-only sibling set makes 'publish' unambiguous enough.

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?

There is one concrete procedural instruction — 'Call get_listing_schema first' — which is genuinely useful for the complex nested payload. However, there is no guidance on when to use this versus other creation tools, no prerequisites about required credentials, and no exclusions.

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