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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, destructiveHint), so the bar is lower. The description adds genuinely useful behavioral context beyond annotations: the shared-account implication that this crosses inbox boundaries created by other callers. No contradiction with 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?

The key scoping constraint is front-loaded in the first clause and the routing guidance is efficient. The long list of returned fields is somewhat redundant given the output schema exists, making the description slightly verbose, but every sentence otherwise earns its place.

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?

Complete for an org-wide fetch tool whose annotations already disclose the read-only/idempotent profile. It explains the shared-account nuance, the difference from the inbox-scoped twin, and what fields come back; with an output schema present, nothing an agent needs to call it correctly 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 100% for both parameters (draft_id and Authorization), so the schema does the heavy lifting. The description lists the returned draft fields (draft_id, inbox_id, to, cc, etc.) which is output-shape info rather than parameter semantics, and with an output schema present it adds little. Baseline 3 is appropriate.

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 opens with a specific verb-resource pair ('Fetches one unsent draft by id') and immediately states the distinguishing scope: it works without naming an inbox and spans every inbox in the account. It explicitly names the inbox-scoped twin get_agentmail_inbox_draft, so an agent can separate this from the many get_agentmail_* siblings without opening schemas.

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?

Gives explicit routing guidance: the organization-wide view is for reaching inboxes other callers created in the shared AgentMail account, and it names the alternative get_agentmail_inbox_draft as the one to use 'when a single inbox is meant.' The selection criterion is concrete and actionable.

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