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

Annotations already declare non-readonly, non-idempotent, non-destructive and openWorldHint=true, so the bar is lower; the description still adds real context: the page is unlisted and not indexed, it stores on this server with no outside service contacted, and the prospect is never messaged. It does not explain whether republishing with the same prospect overwrites the prior page, which matters given idempotentHint=false. No contradiction — openWorldHint=true is consistent with the link being externally reachable even if unlisted.

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 opening clause is well front-loaded, but the tail repeats itself: 'unlisted and not indexed; nothing is sent to the prospect' is restated as 'under an unlisted link; no outside service is contacted and the prospect is never messaged.' Two sentences of the description's length are redundant, though the remaining content is substantive.

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 five-parameter write tool with no output schema, the description covers source data, the preview/confirm contract, publication and hosting behavior, indexing visibility, and the lifecycle handoff to agreement_draft and client creation. Nothing an agent needs in order to call this correctly is missing.

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 80% and the schema already documents title defaults, confirm semantics, prospect name, and the sections structure. The description adds only the provenance of sections ('from audit_prospect'), nothing about period_label or allowed section content beyond what the schema carries. Baseline 3 is appropriate.

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 prospect audit as a branded, shareable page') plus an explicit sibling contrast: 'like create_client_report, but for a business that is not a client yet.' An agent can distinguish this from create_client_report, audit_prospect, and report_template tools without opening any 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?

States the required upstream source ('Takes the sections and fixes from audit_prospect'), the gating behavior ('Previews unless confirm is true'), and the downstream sequence: agreement_draft → signing/paying creates the client, so no create_client is needed. That is explicit when-to-use and when-not guidance with a named alternative path.

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