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

With readOnlyHint=true already covering safety, the description still adds real behavioral context beyond annotations: it requires login, it warns that the public domain has no in-building permission, it discloses that cloud users cannot be chatted with, and it clarifies that score is ranking only, not a quality signal. That is genuinely useful pre-call knowledge. It loses a point for not covering pagination via cursor or any indication of result volume/ordering.

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 short with no filler, and bracket-tagged sections (login note, combination chain) aid scanning. But the compression goes too far: '楼宇默认全网' and 'score仅排序' are telegraphic to the point of ambiguity, and the highest-priority information (login requirement) is front-loaded ahead of what the tool actually does.

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 6-parameter read tool with no output schema, the description covers auth, scope defaults, permission boundaries, the chat limitation and the recommended tool chain — a reasonable skeleton. It remains incomplete on the three items an agent most needs: mode semantics, what a 'match' record contains, and cursor pagination behavior.

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%, so the description needs to compensate and largely does not. It restates includeNetwork and q (both already in the schema) with slight added nuance ('default whole network', 'recall only'), but leaves the mode enum — the parameter that most changes what the tool returns — completely unexplained, along with includeMembers and cursor. An agent cannot tell what members vs latest vs matches produces.

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 never states plainly that it lists matched organization members / cooperation candidates; the verb+resource is only recoverable from the name and title. What it does supply is scope language ('default whole network', 'includeNetwork=false organization only') and a chain step 'organization → this tool → get_creator'. Useful constraints, but the core 'what does it return' statement is absent, and the mode enum (members/latest/matches) that would pin down purpose is never mentioned.

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?

Implied usage is present: login required, q is for recall only ('核对意图资料' – verify separately), cloud users cannot chat, and it slots into the chain after an organization and before get_creator. That tells an agent roughly when it fits. However, no sibling is named as an alternative despite list_organization_members, search_organization_match_people, list_my_organization_memberships and list_organization_match_pairs all being plausible substitutes, so selection is left to inference.

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