List errors users hit

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

Annotations only declare read-only and non-destructive behavior. The description adds much more: grouping by fingerprint, hit count and first/last seen, defects-first sorting, the ours/user/unknown classification policy with 'never guessed', redaction of free text/tokens/emails/creative, input echoes showing shape not content, and scope behavior. This is far beyond what annotations provide.

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 dense but every sentence earns its place: core grouping and row semantics, classification values, redaction behavior, filter options, and access scope. It front-loads the main purpose and uses no filler. The one long sentence is still well-structured and immediately informative.

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 compensates by explaining the row model (fingerprint groups, hit count, first/last seen), sort order, classification meanings, redaction effects, filter opportunities, credit cost, and permissions. An agent has enough to call the tool correctly and interpret the result without further documentation.

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 input schema already has 100% description coverage, so the baseline is 3. The tool description enriches the `kind` enum with concrete examples ('not-connected or out-of-credits', 'vendor 4xx') and the 'never guessed' caveat, and it explicitly names the filterable surfaces. It does not add meaning for `limit` or `since`, so a modest boost to 4 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 opens with a precise definition: 'errors actually recorded against this workspace, GROUPED by fingerprint' and explains the grouping unit, row contents, and sort order. It clearly distinguishes itself from sibling `error_detail` by describing an aggregate, classified list rather than a single error's detail. The verb and resource are unambiguous.

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 gives clear context: read-only, 0 credits, scoped to the current workspace, with optional filtering by surface or kind. It also notes the admin-key expansion to all accounts. However, it never explicitly contrasts with the sibling `error_detail` or states when not to use this tool, so it falls short of full routing guidance.

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