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

With destructiveHint=true already declared, the description adds meaningful context by saying the message is 'queued' (async redelivery rather than a synchronous send) and by citing the exact REST route. It does not say whether this creates a new delivery attempt, whether duplicate delivery is possible, or what permissions are required.

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 tightly written sentences front-load the action, then the usage cue, with zero filler; the REST path is a single conventional line. 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?

All three required params are covered by schema and there is no output schema to explain. However, for a destructiveHint retry operation the description omits outcome behavior (new attempt created, effect on existing attempt history) and failure conditions, leaving the agent with only the surface intent.

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 app_id, msg_id and endpoint_id are fully documented in the schema and the description adds no syntax, format, or ID-type nuance beyond it. Baseline 3 applies when the schema carries the parameter burden.

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 (redeliver/resend) and resource (one message to one endpoint), with scope narrowed by 'one endpoint' so an agent can tell it apart from the broader svix_recover_endpoint. It never names the sibling alternatives explicitly, so differentiation is inferential rather than stated.

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 usual fix after a customer's endpoint was down' gives a clear when-to-use condition that an agent can act on. There is no when-not guidance (e.g. disabled endpoint, already-delivered message) and no reference to svix_recover_endpoint for bulk recovery.

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