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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive), so the bar is lower, and the description still adds real behavioral context beyond them: the meaning of each status, that approved may carry a note when waiting in the manual 'To send' hand-off, and that rows include warnings (open_draft_exists, emailed_N_days_ago) and prior_emails. It stops short of describing pagination behavior or result ordering.

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 and front-loaded: the status vocabulary and its semantics come first, then the warnings/prior_emails fields, then the filter dimensions. The parenthetical asides each carry information, though the single long status enumeration makes it slightly list-like rather than fully scannable.

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 zero-required-parameter read tool with no output schema, the description compensates well by naming the fields returned (warnings, prior_emails, reject_reason, next_cursor implied via schema). The main residual gap is pagination/ordering expectations, which the schema's cursor and limit partially cover.

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 coverage is 100%, so baseline is 3; the description earns above that by expanding the status parameter into the full enum of valid values and clarifying that multiple statuses are comma separated, which the schema only gestures at ('For example rejected,failed'). It does add a little on run_id and contact_id as filter dimensions but nothing beyond their schema text.

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 states the resource (this agent's emails) and enumerates the state model (pending_approval, approved, rejected, sent, failed, cancelled), which makes it clearly a status-listing tool distinct from siblings like list_replies or get_thread. It never uses an explicit verb such as 'list' or 'filter', so the operation is inferred rather than stated.

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?

Usage is implied through concrete cues: 'pending_approval (only when approval is on)', 'rejected (with reject_reason to learn from)', and the three filter dimensions. However, there is no explicit when-to-use guidance, no statement of when not to use it, and no named alternative (e.g. get_thread for a single conversation) to route the agent.

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