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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real context beyond them: data freshness ('read from each mailbox every few minutes'), the downstream side effect that a reply halts follow-ups, and that the call is free. Return payload shape is also described, which annotations cannot cover. No pagination behavior is disclosed, keeping it below a 5.

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-loads the resource and ordering, then packs return fields, freshness, side effect and next-step tool into a tight block. Dense but every sentence carries information; the parenthetical field list is slightly crammed but not wasteful.

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 no output schema, the enumerated return fields are essential and present, and the freshness/side-effect context tells the agent what state means. The remaining gap is pagination and default-page semantics for limit/offset, which the agent must infer.

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 50%: 'since' and 'campaign_id' are documented in the schema, while 'limit' and 'offset' have no description anywhere. The description adds only the implicit ordering ('newest first'), not how limit/offset paginate or what campaign_id filters on beyond the schema's note. 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?

States a specific resource (replies to the business's outreach campaigns) with ordering (newest first) and enumerates the returned fields: sender email/name/company/contact_id, campaign, subject, text, received time, current status. An agent can distinguish this from outreach_campaigns, outreach_get_campaign or outreach_mailboxes without opening the schema.

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 clear operating context: replies are polled from mailboxes every few minutes, answering happens from the business's own mailbox (not via this tool), and interest status is tracked via outreach_set_status — an explicit sibling pointer. It stops short of stating exclusions (e.g. 'do not use for sending replies' is only implied).

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