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

No annotations, so the description carries the burden and does disclose a real workflow consequence: the entry enters a pending state awaiting owner/office approval, plus a hard constraint on backdating. It omits permission requirements, idempotency, and error behavior when no running clock exists, which matter for a mutation with zero annotation coverage.

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 compact sentences, front-loaded with the action, then the workflow consequence, then the edge case. Nothing is padding and the most actionable detail (the 24-hour backdating limit) lands in the reader's mind without a hunt.

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?

The output schema and the approval-state sentence together cover enough for a simple action tool, but with no annotations and 25% schema coverage the definition leaves shop_id/notes semantics and failure modes unexplained. Adequate rather than complete.

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 only 25% (only person_id is documented in the schema), and the description compensates for ended_at well by stating it must be in the past and no more than 24 hours after the start. shop_id and notes get no added meaning, leaving half the parameters underexplained 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?

"Stop a person's running clock" is a specific verb+resource statement that makes clear this is the inverse of timesheets_clockIn and distinct from timesheets_current/decide. It stops short of explicitly naming those siblings, but an agent can place it without opening a 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?

Usage is implied: this applies to a currently running clock, and the retroactive case is addressed with "Forgot to clock out? Give ended_at...". However, it never says what to do when no clock is running (timesheets_clockIn? timesheets_reopen?), nor when the approval flow should route to timesheets_decide instead.

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