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

The description claims the tool can 'modify draft content and recipients' and 'remove the draft entirely', while annotations declare readOnlyHint=true and destructiveHint=false. This is a direct contradiction of the safety profile an agent relies on.

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?

Front-loaded with the resource and action, then a clarifying sentence; reasonably tight. The injected pricing boilerplate and the three-verb sprawl are minor waste but the core is efficient.

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 needn't be described, but the description still misrepresents the tool's mutability and offers no routing to the real update/delete siblings. For a seemingly simple retrieval tool, the definition leaves the agent with a wrong mental model.

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 100%, so draft_id and inbox_id are already documented in the schema. The description adds no syntax, format, or constraint detail beyond that, matching the baseline for schema-covered parameters.

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 resource (email draft in an inbox) and identifier (draft ID), which is clear enough against siblings like get_agentmail_draft. However, it bundles three operations (retrieve/update/delete) into one tool whose name and annotations indicate a read-only GET, so the stated purpose is partly inaccurate.

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?

No guidance on when to use this versus the many siblings that actually cover the claimed operations (patch_agentmail_inbox_draft, delete_agentmail_inbox_draft, get_agentmail_draft). Nothing indicates the read-only scope or prerequisites.

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