audit_log

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds real value by disclosing that refused write attempts are included, but it says nothing about ordering, retention window, or whether results are truncated by recency — gaps that matter for an audit tool.

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 purpose is front-loaded in one sentence, followed by a compact Args block. Every line earns its place, though the 'Args:' formatting is a bit list-like rather than prose-integrated.

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?

An output schema exists, so return values need not be explained, and both optional parameters are documented. However, for a low-annotation-burden read tool with 0% schema coverage, the description still omits result ordering and the meaning of 'recent' (how far back), leaving an agent unable to reason about result scope.

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 0% — the schema exposes 'target' as a bare anyOf string and 'limit' as an integer with only a default — so the description carries the full burden and mostly meets it. It explains that target accepts a purchase order or supplier document ID and that limit is bounded 1-100, which the schema never states.

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 names the resource precisely ('po-guard audit records') and clarifies scope ('every write attempt, including refused ones'), which clearly separates it from the purchase-order CRUD siblings. It lacks an explicit verb (list/read), but the noun phrase is unambiguous enough that an agent can identify it as a read of audit history.

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 word 'Recent' implies a recency scope and 'including refused ones' hints at an investigation/audit use case, but there is no explicit when-to-use or when-not-to-use statement and no mention of alternatives among the 13 siblings. Usage is inferable rather than stated.

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