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

With no annotations, the description carries the full burden, and it does disclose the detection rules in useful detail: identical and near-repeat loops, re-reads of finished items, failing-tool retry streaks, and USD/token caps. What it omits is the decision output shape (there is no output schema) and any statement that the check is a pure, side-effect-free replay — gaps that matter for an agent deciding how to act on the 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?

Two sentences, front-loaded with the core action (replay and decide) before the enumeration of caught conditions. The rule list is dense but each item conveys a distinct guard condition, so little is wasted.

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?

For a tool with nested objects, 33% schema coverage, no annotations, and no output schema, the description is adequate on inputs and detection semantics but silent on the returned decision format and the role of the config object. An agent knows what the tool checks but not what it gets back or how to act on it.

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 description coverage is only 33%, so the description should compensate more than it does. It conceptually maps "agent's tool-call log" to the calls array and "the next call" to next, but never mentions the optional config parameter (agentguard.json) or the semantics of the call fields, leaving the schema to do most of the work.

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 uses concrete verbs ("replay", "decide") against a specific resource (an agent's tool-call log through the AgentGuard loop and budget guard), so the agent knows exactly what the tool does. It does not explicitly name or differentiate itself from the siblings (audit_domain, create_checkout_session, get_remediation_preview), though those are clearly unrelated domains, so a 4 rather than a 5.

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?

"Decide whether the next call should run" implies a pre-execution gating use case, and "before spend" hints at when to invoke it. However, there is no explicit when-to-use/when-not guidance, no mention of prerequisites (e.g., that a full call log must be supplied), and no named alternative.

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