Api webhooks audit sinks replay create

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is structured. The description's 're-emit ... to this sink' adds the meaningful fact that this dispatches historical events outward to an external endpoint and is repeatable/non-idempotent, but it stops there — no mention of volume limits, whether delivery is synchronous, or what happens on sink failure, and the text is cut off mid-sentence.

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 lines is appropriately short, but the definition is under-specified rather than concise: the parenthetical format hint is truncated mid-token ('(ISO'), which reads as a broken tool definition and leaves an unclosed bracket.

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 an externally-facing, non-idempotent replay action with a fully opaque request body and no output schema, the description should carry much more: accepted timestamp format, defaults for 'since', and the effect on the target sink. Annotations cover only the safety hints; the operational contract 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 0% and the body is an opaque anyOf object, so the description is the only source of field names — {since, until?} is genuinely additive. However the format hint is truncated at '(ISO' so the agent can't tell date-only from datetime, and the required 'id' parameter is never explained beyond the vague 'this sink'.

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+resource: re-emitting historical audit events to a named sink. This is clearly distinguishable from the sibling CRUD tools (audit_sinks_create/list/retrieve/destroy) and from batch_action. It loses a point only because the truncated text never clarifies what 'sink' identifier is required or what a 'replay' produces.

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?

No statement of when to use this versus the sink CRUD or batch_action siblings, and no prerequisites (sink must exist, must be enabled, required permissions). Nothing tells the agent when replay is inappropriate, e.g. re-driving a live production endpoint.

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