Error detail

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

Annotations already provide readOnlyHint=true and destructiveHint=false. The description adds valuable context: '0 credits' (cost), 'redacted occurrences' (privacy behavior), and 'shape-only echo of the inputs' (no raw sensitive data returned). These go beyond the annotations and set accurate expectations for a read-only operation.

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, tightly packed. The first sentence front-loads the purpose and contents; the second sentence adds the value proposition. No redundant phrases or filler.

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 one-parameter, read-only lookup with no output schema, the description fully covers what data is returned, where the fingerprint comes from, safety (read-only, 0 credits), and the purpose (bug reproducibility). Nothing essential 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?

Schema coverage is 100% and clearly documents fingerprint as 'the fp value from list_errors.' The description reinforces this by saying 'by fingerprint (from list_errors)' but does not add new semantic meaning beyond the schema. Baseline 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?

States a specific verb and resource: 'One error group in full by fingerprint.' It clearly names the source (list_errors), specifies what is returned (every field, redacted occurrences, status, connector, job id, workspace, shape-only inputs), and distinguishes itself from list_errors by focusing on a single group in full detail.

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 clearly implies a workflow: start with list_errors to get a fingerprint, then call error_detail for the full error group details. It explains why you would use it ('This is what makes a bug reproducible') but does not explicitly list exclusions or compare against alternatives like get_job or list_errors.

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