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

The description claims the call 'sends the same saved message idempotently,' while the annotations declare idempotentHint=false. That directly misleads an agent into believing repeated calls are safe, which is the exact opposite of the structured contract. It also never addresses the destructiveHint=true annotation.

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 trigger, then the preconditions. Every clause carries either scope, precondition, or exclusion information with no filler.

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 mutating tool with no output schema, the description covers triggers, the pre-inspection step, and the never-resend guard. It omits post-retry behavior and says nothing about the safety implications flagged by the annotations, but it is otherwise adequate.

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 both parameters (including the connection credential and its retention rules) are already fully documented in the schema. The description adds no syntax or format detail beyond implying which saved request is resent, so the 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 (resume/retry) and resource (saved pending delivery) with the exact triggering conditions (network failure or restart). It also distinguishes itself from siblings by pointing at request_get for inspection, so an agent can place it in the request lifecycle without opening any 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?

Gives clear when-to-use context (after a network failure or restart) and a precondition ('Inspect request_get first'), plus an explicit exclusion ('completed or cancelled requests are never resent'). It stops short of naming an alternative tool for the non-retry paths, but the routing guidance is strong.

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