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

Beyond the annotations, which only declare the read-only/destructive profile, the description discloses the required key scope and a non-obvious visibility rule: owners/admins see everything, a billing seat only billing rows, a site owner only their sites. That role-based filtering materially changes how an agent should interpret an empty or partial result.

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?

One dense paragraph with the safety profile and scope requirement front-loaded, and the narrowing parameters last. 'Read-only; changes nothing' slightly duplicates readOnlyHint/destructiveHint annotations, but the rest of the text earns its space.

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 naming the returned fields (change, actor, site, result ok/conflict), the permission model that governs row visibility, and the full set of filtering inputs. An agent has enough to call it correctly and interpret the response.

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% (site, limit, since documented; offset bare), so baseline is 3. The description summarizes that site, since, limit (1-200) and offset narrow the result set, largely restating schema content, and offers no additional guidance on offset behavior or since semantics beyond 'ISO time'.

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 resource and content: the account's audit log of API-key operations, listing what changed, the actor, site, and result. That verb+resource+payload framing distinguishes it from the many list_* siblings, which cover entries, forms, submissions, and members rather than audit rows.

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?

Sets clear context with the required key scope (audit:read) and explains who sees what rows, which effectively tells the agent who can use it and what it will return. It does not name an alternative or state a when-not condition, but no plausible sibling overlaps this audit-log niche.

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