Rank Agent

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

Annotations already mark it as readOnly, idempotent, and non-destructive. The description adds valuable behavioral details: the deterministic policy, that on-chain checks are metadata-only and never inflate rank, and that output includes breakdown and verification blocks. No contradictions with 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 a single paragraph that packs significant information without wasted words. It could benefit from bullet points for clarity, but it remains concise and front-loaded with the core policy.

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?

Given the tool's complexity and the existence of an output schema, the description covers the key aspects: ranking formula, XOR requirement, deprecated parameter, and output structure. It lacks a brief note on pagination or sorting, but these are inferable from the schema.

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 67% with 4 of 6 parameters described. The description adds context like the XOR constraint and the deprecation of 'weights', but does not explain 'limit' or 'sortBy' beyond schema defaults. This is adequate but not exemplary.

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 explicitly states the tool ranks agents using a deterministic evidence policy, specifying the exact formula. It distinguishes from siblings like 'find_agent' by requiring XOR between agentIds and query, making its purpose clear and unique.

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?

It clearly states the XOR condition ('Provide EITHER agentIds OR query') and warns that 'weights' is deprecated and rejected. However, it does not explicitly describe when to prefer this over siblings like 'leaderboard' or 'verify_reputation', leaving some ambiguity.

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