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

Annotations already declare readOnly/idempotent/non-destructive, and the description still layers on genuinely new context: no charge, no postage/credit consumption, no mailbox changes, a 20 MB document cap, and the fact that pending-deletion letters are ineligible. All of this is consistent with readOnlyHint=true and is not recoverable from the 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?

Dense, front-loaded, and every clause carries information (cost, payload, input contract, auth, limits, exclusions). The 'No charge.' opener is slightly unusual as a lead but is a high-value qualifier, and no sentence repeats the schema or annotations.

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 present, return values need not be documented, yet the description still describes the ZIP payload well; auth, size cap, eligibility and cost are all covered. Minor omissions remain around partial-failure behavior (one stale version among many) and whether rate limits apply, but nothing essential to correct invocation is missing.

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%, so the description must carry the param meaning, and it does: it names the 'messages' array, its {id, version} shape, the 1–50 range, and adds the non-schema-critical rule that versions must be exact/current (a staleness contract the schema cannot express). It does not restate the 64-hex id pattern, which is fine since the schema covers it.

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?

A concrete verb and resource backed by a precise scope: 'Download 1–50 owned emails as an embedded ZIP' plus the contents (EMLs, PDFs, manifest). The bulk/plural framing implicitly separates it from the singular download_email_letter sibling, but the sibling is never named, so the differentiation is left to inference.

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 gives preconditions ('exact current versions', OAuth or workspace Bearer key, staging keys may download) and exclusions ('pending deletions cannot be downloaded'), which implies this is the bulk-retrieval path. It never states when to use this instead of download_email_letter or get_email_letter, leaving the agent to infer the batch-vs-single choice.

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