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

Goes well beyond the annotations by describing edge-case behavior: sends immediately if the run is already terminal, reports when an email was already sent, and avoids duplicates. This aligns with and enriches the destructiveHint/openWorldHint annotations.

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?

Four sentences with clear hierarchy: core action, primary invocation condition, terminal-state edge case, and duplicate-prevention behavior. No filler or redundant restatement of the name or schema.

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?

With an output schema presentable and annotations covering side effects, the description covers purpose, timing, and idempotency well. However, the complete absence of parameter guidance means an agent may struggle to construct a correct call, especially if it does not already know where job_id and run_id come from.

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 0%, and the description does not explain job_id or run_id, how they relate to each other, or where the agent should obtain them. The parameter names are suggestive, but the description fails to compensate for the missing schema details.

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 ('Email'), a clear recipient ('authenticated account'), and an explicit trigger ('when this run finishes') with enumerated terminal states. No sibling tool overlaps with this purpose, so differentiation is inherent.

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?

Explicitly instructs when to call it: whenever the user asks to be emailed, including after wait_for_run and even after the run has already finished. It does not name exclusions or alternative tools, but no sibling directly competes with this notification behavior.

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