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

Annotations already declare readOnly=false, destructive=true and idempotent=true, so the safety profile is covered. The description adds genuine domain behavior beyond that: a validation rule ('a statement that promises a shorter wait than withinMinutes is rejected') and the approval semantics of the statement field. It still omits overwrite/upsert behavior and how expectedRevision conflicts are handled, which matters for a destructive write.

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?

Four short sentences, front-loaded with the core action and its scope, with no filler. The final sentence ('Do not save a faster reply the user did not approve') largely restates the earlier rejection rule, a minor redundancy.

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 no explanation, and annotations carry the safety profile. But for a 7-parameter destructive write with 0% schema coverage, the description leaves concurrency (expectedRevision), status transitions, and the name field entirely undocumented, which is not quite enough for an agent to call it confidently.

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 0%, so the description must carry parameter meaning, and it only covers withinMinutes ('the approved wait'), statement ('the only reply-time wording that may later be approved'), and implicitly the plan reference. The name, status, and expectedRevision parameters are left completely unexplained in both schema and description.

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 gives a specific verb and resource ('Store the reply window ... for one customer plan'), and the resource noun ('reply window') naturally separates it from the save_customer_plan / save_staffing_promise / save_plan_channel siblings. It does not explicitly name any alternative, so it falls short of full sibling differentiation.

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?

It states a precondition (only what the user explicitly approved) and a prohibition ('Do not save a faster reply the user did not approve'), which implies when this tool is appropriate. However, it never names an alternative sibling or says when to use save_reply_window versus list_reply_windows or save_customer_plan, leaving routing to inference.

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