Error detail

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

Annotations cover read-only/idempotent/non-destructive, and the description adds non-obvious traits: zero credit cost and that occurrences are 'redacted' with only a 'shape-only echo of the inputs' returned. That redaction and shape-only detail is genuine behavioral disclosure beyond the 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?

Dense and front-loaded: the retrieval action and key come first, then return contents, then cost. The closing 'This is what makes a bug reproducible' is mild marketing but does convey intent efficiently.

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?

With no output schema, the description helpfully enumerates the return fields (status, connector, job id, workspace, shape-only input echo), which is what the agent needs to know. Only minor gaps remain, such as ordering or limits on 'most recent occurrences'.

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 100% and the single fingerprint parameter is already documented as 'the `fp` value from list_errors'. The description restates this mapping but adds no format or syntax detail beyond the schema, so baseline 3 applies.

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 retrieval action on a named resource ('one error group in full by fingerprint') and names list_errors as the source of the fingerprint, so it is clearly distinguishable from the sibling that lists error groups.

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 parenthetical '(from list_errors)' tells the agent where the required fingerprint comes from, which is the key prerequisite. It lacks an explicit 'use this when... not that' exclusion, but the usage context is clear.

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