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

Annotations already declare idempotent, open-world, non-read-only, and destructive, so the safety profile is covered structurally. The description adds genuine value beyond that by disclosing the cost model ('never performs another paid search') and the fact that the original supplier call and model-step allowance are preserved, plus the return shape ('results or a concrete review state'). It does not explain why the tool carries destructiveHint=true, how long the wait blocks, or what happens on timeout, which are the remaining gaps.

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?

Two tight sentences with the core action front-loaded and no filler. It loses a point for dense internal jargon ('model-step allowance', 'observed research request', 'concrete review state') that is never defined and slightly slows comprehension.

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-value detail is not required, and annotations cover the safety flags. However, for a six-parameter, nested-object, long-running wait tool that touches paid supplier calls, the description says nothing about blocking duration, timeout behavior, what to do after receiving a 'review state', or how to construct work_id and request_key. Adequate but with clear gaps for a tool of this complexity.

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?

Six parameters with only 50% schema description coverage, and the description names none of them. The undescribed parameters (work_id, arguments.run_id, request_key) get no meaning from the prose, and terms like 'observed research request' and 'original supplier call' are not tied to any field. The description adds essentially nothing beyond the schema here.

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: 'Wait durably for an observed research request', which is clearly distinct from siblings like start_social_research or stop_social_research. It also carves out a boundary ('never performs another paid search'), but it never names the sibling to prefer (read_social_research, wait_for_work), so differentiation is partial rather than explicit.

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?

Usage is only implied: the phrase 'observed research request' hints that this is called after a research request exists, and the 'never performs another paid search' clause hints it is the non-billing polling path. There is no explicit statement of when to choose this over read_social_research, wait_for_work, or quote_social_research_next, and no stated prerequisites or exclusions.

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