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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=true), and the description adds ownership scoping ('calling user's own'), the entry-state gate, and a feature/tier requirement (timeTracking PRO+). It does not explain return values or whether omitted fields are left unchanged, but the added constraints are genuinely useful.

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 tight sentences with no filler: the mutable fields and ownership scope come first, the state gate second, the tier caveat last. Every sentence carries distinct information.

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 the critical preconditions (ownership, entry state, feature tier) that determine whether the call will succeed. It omits partial-update semantics and error behavior, which are the remaining gaps.

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 50%: date and hours carry format/range descriptions in the schema, while notes and entryId are undocumented anywhere. The description enumerates the same three mutable fields the schema already names, so it adds marginal semantic value beyond the structured data.

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?

States a specific verb (Update) plus the exact resource and the fields affected (date, hours, notes) on the caller's own timesheet entry. The state constraint ('DRAFT or REJECTED') implicitly separates it from submit_timesheet, approve_timesheet_entry, and reject_timesheet_entry without needing to name them.

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?

Explicitly gives the when (DRAFT or REJECTED entries) and the when-not (SUBMITTED and APPROVED entries must be returned first), including the required remedy. It stops short of naming the specific sibling tool that performs the return/withdraw step, so the agent still has to infer the next call.

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