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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety aspects. The description adds the cost ($0.002 USD per call) and the context that the result is unverifiable, which are behavioral traits not in the schema or annotations. It does not describe how missing weights or constraints are handled, or error behaviors, but given the strong annotation coverage, the additional transparency is commendable.

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 concise, delivering the core purpose in one sentence, usage restrictions in the next, and the cost in a final clause. It front-loads the primary capability and avoids unnecessary elaboration. The structure is direct and efficient, though it could arguably include parameter guidance without becoming verbose.

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?

For a tool with nested objects, three parameters, no output schema, and no schema descriptions, the description is too thin to fully guide an agent. It does not explain the required input format (the 'candidates' array structure), how to interpret weights or constraints, or what the ranking output looks like. An agent would likely struggle to construct a valid request without further information. The description does not adequately compensate for the lack of schema documentation.

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 0% – no textual descriptions accompany the schema properties. The description only gives a high-level statement that price, reliability, latency, trust, and quality signals are used with weights and constraints. It does not explain the structure of the required 'candidates' array, the meaning of each weight/constraint field, or how they interact. Given the zero coverage, the description must compensate, but it leaves the actual parameter semantics largely unaddressed.

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 clearly states the tool ranks caller-supplied candidates based on price, reliability, latency, trust, and quality, using weights and constraints. It also specifies its intended use for selection routing with unverifiable results. However, it does not differentiate itself from the many similarly-named selection_routing_router siblings (e.g., _3bb0e8d7, _6c37bb83), so it avoids ambiguity about the general task but not about this specific instance.

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 states it is intended for selection routing where the result is unverifiable, and lists prohibited use cases (legal, identity, sanctions, fraud, contractual, regulatory adjudication). This gives clear when-to and when-not-to guidance. It does not mention alternative tools by name, but the prohibitions imply other tools should be used for those domains. It also notes it is a paid resource, which helps with cost-aware decisions.

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