Flush Service Mail Queue

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and openWorldHint=true, so the description's job is supplementary context — and it delivers the auth requirement (developer role) plus the actual underlying Postfix commands, which explains the blast radius of the whole-queue mode. It does not explain what happens to messages whose retry fails, which matters given the destructiveHint flag.

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?

A single tight sentence that front-loads the action, then the two modes with their exact commands, then the permission requirement. No filler and nothing repeated.

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?

Six parameters including a nested requestBody, no output schema, and low schema coverage — the description covers the core id/no-id semantic and auth but says nothing about env/region targeting or what the caller gets back. Adequate to call correctly in the happy path, incomplete for the tool's actual complexity.

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 only 17%, and the one documented field (requestBody.id) is already described in the schema itself, so the description largely restates it. The five other parameters (workspaceSlug, appSlug, serviceName, env, region) get no meaning added anywhere, leaving a real gap for the low-coverage 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 concrete verb ('Asks Postfix to attempt delivery now') and resource (queued mail), and explicitly separates the two operating modes: one message via `postqueue -i` versus the whole queue via `postqueue -f`. It never names the adjacent readServiceMailQueue sibling, so an agent must infer the read-vs-flush distinction from the tool names alone.

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 a clear trigger condition ('instead of waiting for its retry time') and a prerequisite ('Requires the developer role'), which is enough to know when this is the right call. It stops short of saying when NOT to flush (e.g. healthy queues) or pointing at readServiceMailQueue/readServiceMail for inspection first.

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