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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses audit logging, partial-merge behavior ('changes the fields you pass and leaves the rest'), no notifications ('reaches no one'), reversibility ('undone by editing again'), and an auth requirement (Cotlet API key). These additions are genuinely useful, though the audit-log fact is stated twice.

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?

The core purpose is front-loaded, but 'Saved to the audit log' and 'Each edit is saved to the audit log' repeat the same fact, and the 'reaches no one... runs without asking' phrasing is slightly opaque. Trimming the duplicate would sharpen it.

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?

For a mutation tool with no output schema, the description covers preconditions, mutation semantics, reversibility, audit trail, and auth. Return values are not needed given no output schema; only a sharper contrast with sibling tools is missing.

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 entry_id, fields, and ignore_alerts are already documented in the schema. The description echoes the editable fields and adds the partial-update semantics ('leaves the rest'), but adds little beyond the baseline for a fully-covered 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 uses a specific verb (Change) plus resource (start, end, job, task, notes of a shift), so an agent knows exactly what it mutates. It scopes the resource to 'unapproved shift' but does not explicitly contrast with siblings like clockshark_add_time_entry or clockshark_approve_timesheets.

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 real precondition ('works on unapproved shifts only, so unapprove the timesheet first if needed') and signals no confirmation is needed. It gives clear context for when the tool applies, though it never names an alternative tool to use for approved shifts.

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