download_failed_delivery

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds one meaningful behavioral fact — the raw message may not exist because retention is conditional — but says nothing about what happens in that case (error vs. empty result) or about size/format constraints.

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 front-loaded sentence with no wasted words; the resource and format are established immediately and the availability caveat trails the main clause.

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?

An output schema exists, so return values need no explanation, and the read-only annotation covers safety. The main residual gap is the behavior when no stored email exists, which the phrase 'if addy.io stored it' flags but does not resolve.

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 a single parameter at 100% schema description coverage, the schema already defines 'failed_delivery_id' as a UUID. The description adds no further meaning about the identifier, which is acceptable given full schema coverage.

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 ('Download') and a precisely scoped resource ('the raw email (.eml source) of a failed delivery'), which implicitly separates it from get_failed_delivery by signaling raw message content rather than metadata. It does not name the sibling, so the differentiation is inferred rather than explicit.

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 clause 'if addy.io stored it' hints at when the tool is applicable and warns that content may be unavailable, but there is no explicit statement of when to prefer this over get_failed_delivery or what to do when retrieval is impossible. Usage is implied rather than prescribed.

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