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

Annotations only declare readOnlyHint=true and openWorldHint=false, and the description adds substantial context beyond that: login is required, phone/wechat are never made public, private-by-default visibility, the exact fields returned for user verification, and the resume/token-reuse protocol for PARTIAL results. Nothing here contradicts the read-only annotation; it correctly frames this as a non-mutating preview that still requires explicit user confirmation before commit.

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 bracketed prefix '【登录，只预览】' front-loads the two most decision-relevant facts, and each subsequent sentence covers a distinct concern (visibility, confirmation, resume semantics). It is dense and jargon-heavy (cloudAction, PARTIAL, receipt.id) but no sentence is filler.

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?

With no output schema, the description carries the return-value burden and does so by listing the displayed per-person fields and warnings. It covers privacy, confirmation, and resume behavior, but leaves error paths and the schema's own limits (max 20 candidates) unmentioned.

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 25% (only resumeReceiptId is documented in the schema), so the description must compensate — and it largely does: it explains publishCloudProfiles' permission/privacy implications, that resumeReceiptId must equal the original receipt.id while candidate.id is preserved, and that parseToken is reused on retry rather than re-issued. The candidates array structure itself (required id, sourceQuotes) is left to the schema.

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 ('只预览' + network contact intake) and describes exactly what the preview surfaces: per-person create/update, source, supply/demand, cloudAction and warnings. It distinguishes the preview phase from the subsequent 'commit' step, though it never names the sibling tools commit_network_contact_intake or parse_network_contacts explicitly, leaving the agent to infer the pipeline.

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 concrete usage conditions: default is private contacts, publishCloudProfiles=true only with explicit user selection and permission, and PARTIAL edits must use resumeReceiptId with the original receipt.id. It also warns that an initial paste/import request does not count as confirmation, and that a retry should reuse the original token/key rather than re-previewing. Clear when-to-use context, though alternatives are referenced generically ('commit') rather than by tool name.

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