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

Annotations already declare read-only/idempotent/non-destructive, but the description adds substantial context beyond them: required role plus feature flag, org-scoped findFirst that yields 404 for cross-org ids, the before/after payload shape, and the null-not-backfilled behavior of client attribution fields.

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?

Front-loads purpose and payload, then access, then field semantics. The clientSurface enumeration is long but earns its place by disambiguating a return field that no output schema documents. Slightly dense but no wasted sentences.

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 carries the burden of explaining the return payload, nullability, and the clientSurface/clientLabel vs actorType distinction, plus access and scoping rules. Nothing an agent needs to call it correctly 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 there is a single parameter documented as 'AuditLog row id.' The description says 'by id' but adds no format, source, or ambiguity guidance beyond the schema, so the baseline 3 applies.

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 ('Read one AuditLog row by id'), and the singular 'one row by id' implicitly distinguishes it from the sibling list_audit_log and export_audit_log. An agent knows exactly what it retrieves and the required key.

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 clear context for use: single-row lookup by id, with prerequisites spelled out (OWNER or ADMIN + auditLogs feature) and the cross-org 404 behavior. It does not explicitly name list_audit_log as the alternative for querying many rows, so it stops short of full alternative routing.

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