List errors users hit

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

Annotations already indicate read-only and non-destructive, and the description reinforces this with 'Read-only, 0 credits'. It also discloses critical behaviors beyond the annotations: redaction of free text/tokens/emails/creative, grouping by fingerprint with side classification, sorting defects-first, and the workspace scoping with an admin-key exception. These details materially inform the agent's expectations about data safety, output shape, and access boundaries.

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 composed of several dense sentences, each adding a distinct fact (grouping, side classification, redaction, scoping, filters, credits). It is longer than the bare minimum, but every sentence contributes actionable information and the most defining trait (grouping) is front-loaded. It is structured well but could be tightened without losing meaning.

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?

Given that there is no output schema, the description thoroughly explains what the returned rows represent (grouped, with hit count, first/last seen, side, redaction behavior) and how to filter. It also covers access scoping and the read-only nature. An agent has everything needed to call it correctly and interpret the response, making it complete for a list-diagnostics 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?

The input schema covers 100% of the parameters with per-parameter descriptions (kind, limit, since, surface). The tool description mostly references the filter values ('surface', 'kind') without adding new semantics beyond the schema. Since the schema already does the heavy lifting, a baseline of 3 is appropriate; the description does not deepen parameter understanding further.

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 states a specific verb ('list'), a precise resource ('errors recorded against this workspace'), and clarifies the grouping by fingerprint with hit counts and side classification. It distinguishes itself from the many publishing/social tools and even from the sibling 'error_detail' by its aggregate, grouped nature.

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 conveys that this is a read-only, zero-credit diagnostic tool scoped to the workspace, which implies when it might be used. However, it does not explicitly contrast it with alternatives like 'error_detail' or state when not to use it. The usage context is present but not framed as a when/when-not decision, leaving the selection to inference.

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