Retry Email

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

With no annotations, the description carries the full burden and does disclose the critical side effect: a duplicate of the original is created and sent under a new ID, not a true resend of the original. That is exactly the kind of non-obvious behavior an agent needs. Left unstated: permission requirements, whether the duplicate counts toward quota, and what happens to the original's status.

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 sentences, zero filler, and the eligibility conditions are front-loaded ahead of the duplicate-and-new-ID consequence.

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 single-parameter, non-destructive-looking mutation with a fully documented schema and no output schema, the description covers purpose, trigger state, and side effect. It would be complete at 5 if it said what the caller gets back (e.g. the new email ID) or what happens to the original record.

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?

One parameter with 100% schema description coverage; the schema already documents the em_xxx format for id. The description adds nothing about the parameter beyond implying it identifies the original email, 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?

Names a specific verb (retry) and resource (email) and scopes it with precise preconditions: 'hard failed, errored, or was held'. That is enough to distinguish it in spirit from send-email, though no sibling is named explicitly.

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 description clearly states the triggering condition — an email in a failed/errored/held state — which tells an agent when this tool applies. It stops short of naming alternatives (e.g. send-email for a brand new message) or stating exclusions such as 'do not use on delivered emails'.

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