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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds cost information ($0.002 USD per call), which is critical for an agent deciding to invoke. It also explains the intended trust context ('trust unknown'). This goes beyond annotations and adds valuable behavioral context, though it doesn't detail output or side effects (already covered by annotations).

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 tightly written: it opens with the core functionality, then intended usage, then exclusions, then pricing. Every sentence serves a purpose, and there is no redundancy. It's front-loaded with the most important info (what it does) and stays concise.

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 and no output schema, the description lacks explicit information about the return format (e.g., whether it returns a sorted list, just IDs, scores, etc.). It doesn't mention pagination or error behavior (though maxItems is in schema). The ranking behavior is clear, but the missing output contract leaves an agent guessing about what to expect. The cost and intended use are well covered, but the result shape is incomplete.

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 0%, so the description must compensate. It does: it names the signals (price, reliability, latency, trust, quality) and mentions 'constraints and weights', directly mapping to the top-level parameters. This gives semantic meaning to the schema fields beyond their structural definitions. It doesn't exhaustively explain each subfield, but the core semantics are conveyed.

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 explicit price, reliability, latency, trust, and quality signals with constraints and weights. The verb 'ranks' and resource 'candidates' are specific. It also specifies the intended domain (selection routing), but does not explicitly differentiate from the other two ranking API siblings, so it loses a point for not naming alternatives.

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 provides clear intended use ('Intended for selection routing / trust unknown') and explicitly warns against using it for legal, identity, sanctions, fraud, contractual, or regulatory adjudication. However, it doesn't mention alternative ranking APIs or provide decision criteria for when to pick this tool over others, so it's not a full 5.

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