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

With no annotations, the description carries the full burden and delivers: it discloses that each trace is metered separately, that the return is a verdicts array with preserved order, and that a bad trace is isolated without failing the batch. This is valuable behavioral context beyond the raw schema.

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 sentences deliver the use case, capacity, metering, return shape, and failure isolation with zero filler. Information is front-loaded and every clause earns its place.

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 single-parameter tool with no output schema, the description covers return format, error isolation, capacity, and usage context. The schema documents the parameter, and nothing an agent needs to invoke it correctly is missing.

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 provides 100% coverage for the only parameter ('array of trace objects (max 20)'). The description repeats the 20-trace limit and adds output behavior (order preservation) but not much new input-side semantics, so the baseline 3 for high schema coverage 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?

States a specific verb ('Diagnose'), a resource ('SEVERAL traces'), and a capacity limit ('up to 20'). It distinguishes itself from the sibling diagnose_trace by explicitly being the batch variant, and it mentions the per-trace metering tie to that sibling.

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?

Explicitly tells when to use it: 'Use for post-run analysis of many failures at once instead of N round-trips.' This names the alternative behavior (N individual calls) and references diagnose_trace for meter semantics, giving clear routing guidance.

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