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

Goes well beyond the annotations (which only say non-readOnly, non-destructive, non-idempotent) by disclosing that the call creates pending proposals requiring human acceptance, that identities are never revealed, and exactly what credentials are needed. That is the side-effect and privacy context an agent needs before invoking.

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?

One dense but well front-loaded sentence opens with the verb and resource; the parenthetical rule and credential clause are load-bearing rather than filler. Slightly packed, but nothing is wasted.

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 an output schema present, return values need not be explained, and the description covers auth, side effects, and the join prerequisite. Minor gap: no stated outcome for the no-match case or how pending proposals are surfaced, but the core is complete.

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 67%, and the enum meaning for direction is already documented in the schema. The description only reinforces editToken's role as an alternative credential, leaving modelId and direction semantics 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?

States a specific verb and resource -- find complementary PEOPLE for the connected person -- and adds the distinct mechanism (queued pending proposals). It clearly differs in kind from generic find_people, but never names the very similar sibling find_complementary_thinkers, so the agent must infer the distinction.

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 the governing rule (agents propose, humans accept in the hub) and prerequisites: OAuth as owner or the model's editToken, and the target person must have joined introductions. It does not explicitly say when to prefer this over find_complementary_thinkers or find_circles.

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