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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing the cost ('$0.002 USD per call') and the behavioral boundary that this tool only ranks and does not select. No contradiction with annotations exists.

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?

Three sentences, each earning its place: function, scope boundary, then exclusions plus cost. The core action is front-loaded and there is zero filler or repetition of schema content.

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?

The tool is complex (nested candidates, weights, constraints, up to 500 items) and has no output schema, yet the description never mentions the return format — what a ranked result looks like or whether scores are included. The rich annotations and the cost/scope disclosures cover a lot, but the missing output semantics is a real gap for an agent aiming to invoke and interpret the call correctly.

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?

With 0% schema description coverage, the description carries the burden, and it does connect the dotted lines by mapping the five signals (price, reliability, latency, trust, quality) and mentioning 'constraints and weights'. However, it does not explain what a weight means, how constraints combine, the significance of permission_ok/payment_supported booleans, or the interpretation of the ranking output — leaving key parameter semantics open.

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 opens with a specific verb+resource: 'Ranks caller-supplied candidates' and enumerates the exact signals (price, reliability, latency, trust, quality) and inputs (constraints, weights). The phrase 'cannot select' explicitly distinguishes it from the many selection_routing_router_* siblings, so an agent can immediately tell this is ranking, not decision-making.

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 gives clear when-to-use context ('Intended for selection routing') and an explicit when-not-to-use list ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'). It does not name a specific alternative tool by name, but the exclusion list plus the 'cannot select' boundary routes agents away from routers and policy engines strongly enough.

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