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

With no annotations supplied, the description carries the full burden and does substantial work: it declares the required actor (authenticated organization matchmaking staff), the two-step preview/confirm write protocol, the optimistic-concurrency revision contract, and the need to re-confirm after changes. It also enumerates side effects it deliberately does not perform. It stops short of describing what happens on a stale revision or what the confirm response returns.

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 text is dense and front-loaded with the behavioral constraint before the mechanics, and every clause carries information (prohibition list, revision protocol, confirmation flow). Semicolon-separated clauses make it dense but not padded; there is little that could be cut without losing meaning.

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 9-parameter, 5-required mutation with no annotations and no output schema, the description covers the permission model, the preview/confirm safety flow and the revision contract, which are the highest-risk elements. However, five parameters remain undocumented anywhere, and the return/conflict behavior is unspecified, so an agent could still mis-supply stage or previewHash on first call.

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 description coverage is 0% across 9 parameters, so the description has to compensate. It does explain the two hardest ones — revision (take the current record, null on first write) and preview (preview before confirming) — but leaves stage, note, consent, userId, organizationId, proposalId and previewHash entirely to the bare schema, so an agent still cannot infer enum semantics or the purpose of previewHash from the text.

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 states a concrete verb and object: record the contact results that have actually occurred ('记录本人已发生的联系结果'), scoped to the caller's own outreach. It separates itself from neighboring write tools by explicitly denying invitation sending, consenting, payment, invoicing and check-in, so an agent can distinguish it from invite_organization_meetup_to_activity or check_in_attendees. The resource itself (meetup outreach record) is only implied via the name/title rather than restated, which keeps it just 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?

It gives a clear when-to-use condition (after a real contact attempt has happened) and explicit when-not conditions (no fabrication, no proxy calling), plus the required workflow of preview-then-confirm and re-confirmation on change. What is missing is any named alternative sibling tool for the cases it excludes, so the routing guidance is stated as prohibitions rather than redirections.

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