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

With no annotations provided, the description carries the full burden of disclosing behavior, but it only states that the tool ranks agents by trust score and includes DNA summaries. It doesn't disclose whether this is a read-only operation, whether the leaderboard is real-time or cached, whether 'DNA summaries' means nested data structures with a comparison basis, or whether limits beyond 10/50 affect behavior. The description adds minimal behavioral context beyond the input schema and its own top-line purpose.

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, compact sentence with no filler. It front-loads the most critical information: what the resource is, the ranking metric, and the included data ('DNA summaries'). One could argue it could clarify 'DNA summaries,' but for an 11-word description, it's efficient and well-structured.

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 there is no output schema and no annotations, the description should explain what a caller receives (e.g., fields per agent, how DNA summaries are structured) and why this tool exists in context. The current text is a title-like statement, not a complete tool contract. The single optional parameter is well-documented, but the result shape and usage context are unresolved, making this inadequate as a standalone tool definition.

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?

The schema description for 'limit' is 100% covered, clearly stating the default (10) and maximum (50). The tool description mentions ranking agents by trust score, which loosely contextualizes the limit parameter as controlling the page size of that ranking, but it doesn't expand on returned format or edge cases. Since schema coverage is full, the baseline of 3 is appropriate; the description doesn't add significant parameter semantics beyond the schema.

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 names a specific resource ('agent trust leaderboard'), a verb ('ranked'), and the ordering criterion ('trust score'), with 'DNA summaries' hinting at included data. It distinguishes itself from sibling tools like soul_profile or soul_insights, which likely serve different purposes, though it doesn't explicitly contrast itself. The context signals confirm a very limited output, so the core purpose is clear.

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 implies a read-only listing use case but provides no explicit guidance on when to choose this over related tools like soul_bounties or soul_stack_feed. Specialized terms like 'trust score' and 'DNA summaries' are left undefined, and there's no mention of prerequisites or when this tool is the right choice versus alternatives. This is implied usage only, not explicit routing guidance.

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