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

Annotations only give a generic safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=false); the description adds the non-obvious lifecycle semantics that the script becomes frozen after schedule approval and that the assistant is constrained to this script plus read_schedule facts. That is real behavioral context beyond the annotations. It does not explain why the operation is flagged destructive or how repeated writes behave, so it is not a full 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?

Three sentences, no filler, and the core action leads. The second sentence packs a locking rule plus a forward reference into one dense clause, which is slightly harder to parse than it needs to be, but nothing is wasted.

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 the description supplies the freeze-after-approval rule and the assistant-scope constraint that the annotations cannot express. The remaining gap is what the tool does when called before approval or on an already-approved schedule, which is central to a tool whose siblings include commit_schedule.

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 carries the burden, and it only partially does: 'script' is glossed as what the assistant may tell the client, but the 2000-character limit and the scheduleId (uuid) parameter are never explained. The partial gloss compensates somewhat but leaves the identifier parameter undocumented in both places.

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 a concrete verb and object: record the script governing what the assistant may tell the client about deposit and payment dates. That is specific enough to separate it from read_schedule and the schedule-mutation siblings. It loses a point because it points at 'revise_client_script', which is not in the sibling set (the closest siblings are suggest_schedule_change / accept_schedule_change), so the cross-reference is ambiguous.

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 communicates an important boundary condition — after the schedule is approved, different wording is refused until an accepted revise_client_script suggestion — which tells the agent when writing is effectively blocked. However, it never states positively when to call this tool versus the many schedule-editing siblings, nor what happens if invoked before approval. Usage is implied rather than prescribed.

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