List errors users hit

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantially more: redaction of free text, tokens, emails and creative before storage; the ours/user/unknown attribution rule including that unknown is 'never guessed'; zero credit cost; and the admin-key visibility boundary. These are real behavioral disclosures an agent needs to interpret rows correctly.

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?

Information-dense and front-loaded: purpose first, then row semantics, then redaction, then filters, then cost/scope. Every sentence carries content, though the dense parentheticals make it slightly heavier than necessary.

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?

No output schema exists, so the description must describe results — and it does: one row per fingerprint, hit count, first/last seen, defects-first ordering, and per-row attribution. Combined with 100% parameter coverage and safety annotations, an agent has everything needed to call and interpret this tool.

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% and both enums are documented in the schema, so the baseline is 3. The description restates the kind and surface categories but adds little syntax or format meaning beyond what the schema already provides.

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?

Names a specific verb and resource ('list errors actually recorded against this workspace') and adds the distinguishing mechanic — grouping by fingerprint with hit counts and first/last seen, sorted defects-first. An agent can differentiate it from the sibling error_detail, which returns a single failure, without opening either schema.

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?

It explains how to narrow results ('Filter by surface or kind') and states cost/scope, but never states when to reach for this over error_detail or what situation calls for it. Usage is implied rather than directed at an alternative.

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