Read the audit log

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real context beyond them: required scopes (coach:read, luca:read), redacted data sensitivity, workspace override behavior, and newest-first ordering. Repeating the idempotency fact adds nothing, but the redaction and scope disclosures are genuinely useful.

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 first sentence front-loads what the tool is, the second adds the routing rationale, and the operational block packs scopes and workspace behavior compactly. Mild waste in restating idempotency already asserted by annotations.

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?

Output schema exists, so return values need no explanation, and pagination/truncation behavior is documented in the maxPages schema field. Scopes, redaction, ordering, and workspace override are all covered; the one remaining gap is that actorType/action have no enums or valid-value guidance, so an agent doesn't know what values to pass.

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 75% with the entire nested query object's seven filter fields undocumented, so the description carries meaningful load by naming actor type, action, action prefix, and target as the filterable dimensions, plus the workspaceId/workspaceSlug override. It still doesn't clarify cursor/limit semantics or differ action vs actionPrefix, but it substantially compensates.

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 (read the coach-visible audit trail), specifies ordering (newest first), enumerates the filter dimensions, and carves out a distinct niche as 'the one read that spans every domain' — clear against the many domain-specific list siblings.

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?

Gives a concrete when-to-use rule: check what a previous run did instead of replaying each list route. The alternative is described as a category ('each list route') rather than a named sibling, and there are no explicit when-not conditions, so it falls just short of the top mark.

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