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

With no annotations, the description carries the full load and does well: it discloses the owner-only restriction, an auth/link prerequisite, the 80-point gating threshold, that the listing is a preview not yet for sale, and the exact degradation behavior on a miss. The auth wording ('Needs the signed-in link... it answers with how your person connects it') is too garbled to be reliably actionable, which keeps this from a 5.

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 operational content is dense and earns its place, but the first two sentences about the signed-in link are confusing filler that an agent cannot act on, and the rest is delivered as one long unbroken block. Front-loading the actual publish action before the link preamble would improve it.

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?

An output schema exists, so return values need not be explained, and the gating/eligibility rules are covered well. Gaps remain around pass_id's meaning, what the preview options actually change, and the unresolved auth prerequisite, which an agent needs in order to invoke this correctly.

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 only 50% and options is a free-form object (additionalProperties: true), so the description's enumeration of the accepted keys — teaser, innovative, industry_code, use_case, tags, technologies, sub_code, price_usd — adds real value the schema does not provide. The required pass_id is left entirely unexplained, and the referenced pivot_of is never tied to any parameter of this tool.

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 core action is stated with a specific verb, resource and scope: 'list a finished, rated marketplace pass in the Co-Invent marketplace as a preview (shown, not yet for sale)'. However, it never distinguishes itself from the near-identical sibling co_invent_publish_pass, and the opening lines about the signed-in link muddy rather than sharpen the purpose.

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?

Strong eligibility guidance: owner-only, and only for a pass at commercial potential 80+ with real evidence, cited prior-art separation, and a named buyer and price. It also describes the failure path (explain why, offer one pivot via co_invent_start_pass with pivot_of, drop the brief on a second miss). Still missing explicit guidance on when to choose this over the sibling co_invent_publish_pass.

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