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

Annotations only declare idempotentHint=true and destructiveHint=false, yet the description adds substantial context beyond them: state is re-checked inside a lock, submission requires the previewHash echoed from preview, some actions are reserved to the target person, and consent recording has hard evidentiary preconditions. The proxy prohibition ('不代同意或付款') is exactly the kind of constraint the annotations cannot express.

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?

It is front-loaded with login and purpose and contains almost no filler, but it is a single semicolon-chained run-on mixing workflow, authorization rules, evidence requirements and completion conditions. Given the tool's complexity a lightly list-structured version would be far easier to apply than this dense block.

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 12-action mutation tool with no output schema and thin annotations, the description covers the hardest parts: the preview handshake, lock re-check, per-action authorization, consent evidence and completion preconditions. It falls short of full completeness only in leaving most action enum values and their individual preconditions undescribed.

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 14 parameters, so the description carries the burden, and it explains only a subset: preview/previewHash/consent as a submission handshake, targetConsentObtained plus note, and note content for consent recording. The 12-value action enum is largely unglossed (accept, decline, propose_target, schedule, confirm, propose_observation_start, cancel, dispute get no explanation), and location, scheduledAt, durationMinutes, targetUserId/targetContactId and observationStartedAt are never mentioned.

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 specific verb and resource: 推进逐单引荐 (advance a single introduction), which implicitly separates it from the create_/get_/list_network_introduction siblings. It does not name any sibling explicitly, so an agent still has to infer the boundary against create_network_introduction and get_network_introduction from the name alone.

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?

Gives an explicit two-step protocol (preview first, then resubmit with preview=false, previewHash and consent=true after the user verifies order/action/evidence) and per-action restrictions: target_accept/target_decline are target-only, record_target_consent requires a prior explicit user statement plus targetConsentObtained=true and a note describing time and method. It also states the when-not conditions — no completion until both parties confirm and the observation period elapses, and never act as proxy for consent or payment.

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