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

Annotations only supply destructiveHint=true; the description adds the non-obvious trait that this starts a background task rather than completing synchronously, plus how to track it. It does not say whether replayed messages can duplicate deliveries or whether the operation is reversible, so a point is withheld.

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?

Three sentences, zero filler, with the core action and scope front-loaded before the async caveat and the API route. Every sentence earns its place.

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 4-parameter mutation with no output schema, the description covers the async nature and the follow-up tool needed to observe results. It omits what happens to already-delivered messages and any permission requirements, but the essentials for correct invocation are present.

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 100%, so the schema already documents app_id, endpoint_id, since and until. The description only restates 'since a timestamp' and the window concept without adding format or default details beyond the schema.

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 ('Replay') and resource scope ('every failed message for one endpoint since a timestamp'), which cleanly separates it from svix_resend_message (single message) and svix_list_attempts_by_endpoint (read-only). The REST route reinforces the exact operation.

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?

Gives the triggering condition (failed messages on one endpoint since a timestamp) and explicit follow-up guidance ('follow it with svix_list_background_tasks'), which is real operational context. It stops short of stating when NOT to use it versus svix_resend_message, so it falls below a 5.

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