exceptions

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

Annotations already convey read-only, idempotent, and non-destructive behavior, so the description adds meaningful context by stating that SWALLOWED is claimed only when the recording proves it. This reveals an evidence-based classification policy and a conservative bias in the tool's output.

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 two short sentences with no filler. The core actions are front-loaded, and the evidence rule about SWALLOWED earns its place by conditioning how agents should interpret that category.

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 read-only inspection tool with fully documented parameters and safety annotations, the description adequately conveys what the tool returns: classified raises with reasons. It does not detail output formatting or ordering, and it lacks sibling routing, so it is not fully complete.

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 description coverage is 100%, so the parameters are already documented in the schema. The description adds no additional parameter-level meaning, such as format or interaction between run, after, and limit, 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 specifies that the tool classifies exception raises into categories (swallowed, uncaught, re-raised, propagated, ambiguous) with reasons, which is a specific verb+resource pairing. It does not explicitly differentiate itself from sibling tools like flow or info, though the exception-classification focus is fairly distinctive.

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?

There is no guidance on when to use this tool versus alternatives. It does not mention sibling tools, preconditions such as an active run, or scenarios where another tool would be more appropriate; the intended use is only weakly implied by the name and description.

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