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

Annotations mark this as a non-read-only, idempotent, non-destructive mutation. The description adds genuinely useful behavior beyond that: the state gate (pending approval only), the error behavior (refusal with reason for approved/rejected periods), and the downstream effect (entries become editable again). What it does not cover is authorization requirements or what a successful recall returns, but the state gating already exceeds the annotation bar.

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?

Two sentences, with the operation and its undo framing front-loaded, followed by the precondition and failure mode. No filler, and the argument's origin is appended last where it belongs.

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 covers the operation, the state gate, and the failure path. The remaining gap is authorization/permission context for the userId-less case and what the caller should do after a refusal, which keeps it from a 5.

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 100%, so the baseline is 3. The description's only parameter detail, submissionId's provenance ('a filing result or a timesheet read gave'), duplicates the schema's own wording rather than extending it, and userId is left entirely to the schema.

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 effect ('pulls a filed timesheet back... the undo for filing it') plus the resource scope (a timesheet still awaiting approval). It distinguishes itself from submit_timesheet, return_timesheet, and approve_timesheets by naming the inverse operation explicitly, so an agent can route 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?

It clearly states the operating precondition ('while it still waits for approval') and the failure condition ('an approved or rejected period is refused with the reason'), which is strong when-to-use guidance. It does not name sibling alternatives such as return_timesheet, so it falls just short of the explicit alternatives coverage a 5 requires.

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