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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's burden is lower. It adds real value by disclosing the output shape — classification, severity class, cause, and recommended action — which is essential since there is no output schema. It does not mention any limits on input size or how ambiguous/unknown bounces are handled.

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: the first front-loads the action, the taxonomy of outputs, and the per-item result fields; the second is a single useful operational instruction. No filler or redundancy.

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-input tool with no output schema and strong annotation coverage, the description supplies the important missing piece — what the return values mean. Only minor gaps remain (behavior on unrecognized bounce text, order of returned items).

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?

With one parameter and 100% schema coverage, the schema already documents the field fully. The description's 'separate several bounces with a blank line' restates part of the schema and actually omits the '---' separator the schema also permits, so it adds no meaning beyond the 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?

The description uses a specific verb ('Classify') with a specific resource ('bounce messages (NDRs)'), enumerates the exact categories it produces, and states what each result contains (hard/soft/block, cause, remediation). It is clearly distinct from siblings like analyze_headers or analyze_dmarc_report 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?

The context is clear — the tool takes pasted bounce message text — and the final sentence gives concrete operational guidance on handling multiple bounces. What's absent is any explicit when-not condition or comparison to alternatives (e.g. analyze_headers for full raw messages, check_suppression for list hygiene), leaving routing to inference.

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