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

Adds behavior beyond the annotations: the call is asynchronous and returns a durable run ID immediately, and retry_required dispatch must reuse the same client_request_id. This explains and reinforces the idempotentHint=true. It is a write-triggering operation consistent with readOnlyHint=false.

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?

Four front-loaded sentences ordered as purpose, prerequisite, return, retry. Each conveys distinct operational information with little waste, though the jargon ('bounded research swarm') adds mild density.

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?

An output schema exists, so return values need not be detailed, and the description still usefully flags the run-ID return and retry contract. For a complex tool with a nested limits object, defaults for limits/categories are left to the schema, which is acceptable.

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%. The description adds meaning for the person_id/team_id relationship (self vs other person requires a Team) and the client_request_id retry contract, but says nothing about limits, question, or categories, which the schema already partially documents.

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+resource (research and save cited person knowledge) and clarifies the mechanism (noticed's bounded research swarm). It distinguishes itself from enrich_person/submit_enrichment_research by scope, but does not name a sibling explicitly.

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 clear conditional routing: self works before connecting profiles, while other people require a selected Team. It also gives a specific retry rule (repeat with same client_request_id, do not create a new run). No explicit naming of research_status/cancel_research as alternatives, so not a 5.

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