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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=true, idempotentHint=true), so the bar is lower. The description still adds a genuinely useful semantic boundary — handling does NOT assert the message was delivered — which no annotation conveys. It stops short of saying what state the follow-up lands in or what an ineligible follow-up returns.

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?

A single compact sentence with the primary action front-loaded and the clarifying negation attached immediately after. Zero filler.

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 need not be explained, and annotations carry the safety profile. However, "eligible" is left undefined and the post-condition (whether the follow-up is cleared from the queue, and what happens on an ineligible call) is unstated for a destructive mutation.

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% and each parameter description already points at its source tool (agents_list, engineering_follow_ups, inbox_list/conversations_search). The description adds no parameter-level meaning, so the baseline 3 applies.

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 verb and resource ("Marks ... follow-up handled") and narrows scope to "eligible undelivered" follow-ups. It does not explicitly distinguish itself from the sibling engineering_follow_up_retry, leaving the agent to infer the split between acknowledging versus retrying a delivery.

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 qualifier "eligible undelivered" implies the precondition for use, but the description never names an alternative or exclusion — notably engineering_follow_up_retry, which is the obvious fork in behavior. Usage is implied rather than routed.

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