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

No annotations are present, so the description bears full responsibility for behavioral disclosure. It does reveal that recommendations carry an evidentiary basis ('observed liveness or unverified'), which helps an agent assess output trustworthiness. However, it does not disclose whether the tool performs live network checks, whether it has side effects or authentication needs, or any rate limits.

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?

The description is two sentences with no waste. The core purpose and return shape are front-loaded, followed by a useful routing note about search_agents. Every clause earns its place.

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 or annotations, the description must compensate by describing the return value and usage context. It gives a high-level return shape and a sibling distinction, but leaves out parameter semantics for three parameters, the detailed structure of the ranked candidates/recommendation, and any failure or edge-case behavior. It is minimally viable but has clear gaps.

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 only 40%: remoteOnly and requireLive have descriptions, while need, limit, and protocols do not. The description's 'Given a task and constraints' is generic and adds no specific meaning for the undocumented parameters, leaving an agent to guess at the format or effect of need, limit, and protocols.

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 states a specific verb and resource: 'returns ranked candidates and a recommendation' for the 'best available agent for a task'. It also differentiates itself from search_agents by noting this tool is preferred when the result will be called, making its role distinct among siblings.

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?

The description explicitly says 'Prefer this over search_agents when you intend to call the result,' providing a concrete condition for choosing this tool over the most similar sibling. It does not cover when-not conditions for other siblings like get_agent or claim_agent, but the primary alternative is addressed.

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