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

Annotations already flag this as a non-read-only, open-world, non-idempotent write, so the safety profile is partly covered. The description adds genuinely useful behavioral context beyond that: drafts are private, nothing becomes public without the provider's consent, no agent id is retained, and earn=true triggers a 25% referral commission for 12 months. The only gap is no disclosure of what the call returns or review timing.

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?

The content sprawls across long, marketing-flavored sentences, with the concrete action and the referral caveat buried mid-paragraph. 'Free, no key' and the commission asides dilute the front-loaded signal an agent needs, so it is over-long rather than efficient.

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 four-parameter write tool it covers privacy, provider consent, and the opt-in referral mechanic, which are the key behavioral concerns. It still omits what a call produces (draft reference? confirmation?) and any output expectations, so it is adequate but not fully complete.

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 schema already documents all four parameters, making 3 the baseline. The description does elaborate 'earn' beyond the schema's terse 'terms 6c' reference by spelling out the 25%/12-month referrer arrangement, but it adds nothing for url, note, or looked_for.

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?

The description implies submitting a third-party service ('Name the service... an MCP server, an OpenAPI document or an x402 endpoint'), which distinguishes it from siblings like create_listing or import_service that concern your own listing. However, no explicit verb like 'submit' or 'tip off' anchors the action, and the opening line 'Free, no key' delays the actual purpose, leaving the agent to infer the operation.

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?

It gives a recognizable trigger ('Found what agents look for somewhere else?'), which implies when to use it. But it never names alternatives such as create_listing or import_service, nor does it state when NOT to use this tool, leaving the routing decision to inference.

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