check_replay_safety

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals a single gating condition but does not state whether the tool actually performs a block, returns a decision, is read-only or mutating, requires special permissions, or what happens when the condition is not met. The behavioral picture is substantially incomplete.

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 description is a single front-loaded sentence with no wasted words. However, given the tool's complexity and the completely undocumented parameters, it is too sparse to be appropriately sized for the task.

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. But with no annotations, 0% parameter description coverage, and two undocumented parameters, the one-sentence description leaves critical context missing for correct invocation.

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 0%, and the description does not mention either parameter. The meaning of 'state' and 'side_effect_state' is left entirely unexplained, so the description fails to compensate for the missing schema documentation.

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 states a conditional action (block blind replay) tied to a specific resource and conditions (side effects or request lineage unresolved). However, the tool name suggests a safety check rather than an enforcement action, and no sibling tool is mentioned or contrasted. The purpose is somewhat inferable but not sharply distinguished from siblings like validate_evidence or resolve_precedence.

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 description implies a trigger condition (when side effects or request lineage are unresolved), but it gives no explicit when-to-use guidance, no when-not-to-use guidance, and no alternatives among the sibling tools. An agent must infer the context entirely from the name and vague condition.

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