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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, openWorldHint=true), the description discloses that each run invokes a real LLM and records exposure, that results beyond the cap are truncated, and that contact info is excluded. This explains the side effects that justify the non-read-only, non-idempotent flags rather than merely restating them.

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?

Highly front-loaded, opening with the login requirement and the core scope before the caveats and sibling pointer. The 【】 markers and telegraphic phrasing pack a lot in, though the density borders on terse and slightly reduces immediate readability.

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 burden and does describe key return traits: candidates plus matchedNeeds, truncation behavior, and the absence of contact info. A short note on exposure/limit reporting could complete it fully, but it is adequate for a two-param aggregation tool.

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 100%, so both needIds and limitPerNeed are already documented in the schema. The description is consistent with the schema (max 5 run, excess truncated) but adds little param syntax beyond it, so the baseline 3 applies.

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?

States a precise verb+resource+scope: aggregates candidate people and matchedNeeds for up to 5 of my OPEN needs. It explicitly contrasts itself with the sibling get_need_recommendations ('单需求深读用get_need_recommendations'), so an agent can distinguish the two without opening either 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?

Gives explicit when-to-use and when-not: use this for batch aggregation across my needs, use get_need_recommendations for a single-need deep read. It also states operational constraints ('无cursor勿轮询' – no cursor, do not poll), which tells the agent how not to invoke it.

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