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

With no annotations, the description carries the full burden. It discloses that results are ranked by consistency, derived from real traffic, and account-specific. This goes beyond a generic 'list' statement. It doesn't mention return format, but the core behavioral traits are well covered.

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?

Two dense sentences front-load the primary action and then enrich with examples and data source. Each sentence earns its place, though the second sentence could be slightly trimmed without losing value.

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 low-complexity read-only tool with high schema coverage, the description is complete enough. The absence of an output schema is mitigated by the clear 'list' semantics and explanatory context about ranking and source. No critical gaps remain.

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 input schema already provides full coverage (100%) with clear descriptions for both schema_id and version. The description adds contextual meaning but does not explain parameter-specific syntax or defaults beyond what the schema already says, so the baseline score of 3 is appropriate.

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 action ('List the correlation-key candidates'), the resource ('a learned schema'), and provides concrete examples (Stripe payment_intent, GitHub PR) to illustrate the identifier-like fields. This makes it distinct from sibling tools that manage buckets or events.

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 explains when to use this tool: 'to group events by when reconstructing a lifecycle.' It also notes the data is 'derived from real traffic,' implying it reflects actual account data. While no explicit alternative is named, the use case is clear enough to guide tool selection.

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