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

Annotations give only destructiveHint=true plus a title, so the description usefully adds that this runs as a background task and must be polled via svix_list_background_tasks. It does not disclose the destructive side of a replay (possible duplicate deliveries to the endpoint, or permission requirements), which is the main behavioral gap.

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 short sentences, front-loaded with the action and scope, then async behavior, then the raw REST route. The REST endpoint line is the least load-bearing for an agent that only invokes the MCP tool, keeping it just below a perfect score.

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-param mutation with no output schema, it covers the essentials: what is replayed, the time window, and that completion must be tracked via svix_list_background_tasks. Remaining gaps are side-effect details (duplicates, permissions, partial failure) rather than anything needed to construct the call.

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% — since/until are documented as ISO-8601 window bounds, app_id and endpoint_id as identifiers. The description restates the 'since a timestamp' window without adding format, default, or edge-case detail beyond the schema, so baseline 3 applies.

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 and resource with scope: 'Replay every failed message for one endpoint since a timestamp.' The scope ('every failed message for one endpoint') implicitly separates it from svix_resend_message, which re-sends a single message, so an agent can pick correctly without opening either schema.

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?

Use context is clear (bulk replay of failures for one endpoint since a timestamp) and it names the required follow-up tool, svix_list_background_tasks, which tells the agent the call is asynchronous. It stops short of explicit when-not guidance, e.g. when to use svix_resend_message instead for a single message.

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