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

With no annotations, the description must disclose behavioral nuances. It states that replay does not re-verify the event (original delivery already passed verification), and that the new run's trigger_ref references the original run id. It also notes that a paused delivery has no run to replay. However, it does not disclose side effects like creating a new run record, potential idempotency, or failure modes.

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 two sentences with no filler. The first sentence fronts the core purpose and behavior; the second addresses the webhook special case. Information is efficiently packed without redundancy, though the second sentence is slightly long.

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?

Given the tool's moderate complexity (4 params, no output schema, no annotations), the description covers the main usage scenarios and parameter selection. However, it does not explicitly state that either run_id or (id+row_id) is required (the schema lists no required fields), nor what happens if both are provided. It also lacks guidance on locating row_id beyond a couple of examples, and does not describe return values or errors.

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 100%, so the baseline is 3. The description adds meaningful usage context beyond the schema: it explains that id and row_id are paired and only for webhook triggers, and that run_id is for event/message triggers. It also clarifies tenant_key's conditional necessity (only when no Authorization header). This extra guidance improves parameter understanding.

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 clearly states the tool's action: re-running a past event- or message-triggered run using its exact stored event/envelope. It also differentiates from sibling tools like host.trigger.fire (which presumably creates new runs) and host.runs.get (which retrieves run info) by focusing on replaying an existing run's payload. The webhook vs event/message distinction is explicit.

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 gives clear guidance on when to use webhook parameters (id and row_id) versus run_id for event/message triggers, explicitly stating that webhook triggers lack a run to replay from. It also mentions tenant_key requirement context. It does not explicitly name alternatives (e.g., 'use host.trigger.fire to create a new run'), but the parameter-selection guidance effectively routes the agent to the correct usage.

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