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

Given that readOnlyHint=true and destructiveHint=false already cover the safety profile, the description adds genuinely useful behavioral context: results are 'newest first,' the outcome filter separates delivered from non-delivered mail, and each row contains id, sender, recipients, subject, outcome, and timestamp. This is beyond what annotations provide and helps the agent set expectations.

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 entire description is two sentences with zero fluff. Use cases are front-loaded in the first sentence; ordering, filter semantics, and output fields are in the second. Every phrase 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?

For a tool with three optional parameters and no output schema, the description is complete: it states scope (workspace emails), ordering, filtering semantics, and row contents. It does not explain pagination via `before` or the default `limit`, but those are documented in the input schema, so the description's job is largely done.

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 the baseline is 3, but the description adds semantic value by explaining the outcome filter's meaning and that accepted means handed to the mail system while the others did not go out (or are scheduled). This clarifies the enum values beyond the schema's own descriptions, lifting the score to 4.

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 specific use cases ('what emails they sent, what went out recently, or which sends did not go out or are still scheduled') and clearly identifies the resource (emails in the member's workspace). It distinguishes itself from the sibling connections_email_get by noting that each row carries an id for that tool, so the agent can tell list from get.

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 provides explicit when-to-use scenarios and clarifies how the outcome filter should be interpreted ('accepted = handed to the mail system; the others are sends that did not go out'). It does not explicitly say 'use connections_email_get for a single email' or state when not to use this tool, but the pointer to the id for email_get is a useful routing hint.

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