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

Annotations only say readOnlyHint=false, destructiveHint=false, leaving behavioral disclosure entirely to the description. The description reveals significant side effects: setting APPROVED/REJECTED stamps approved_by/approved_at, ownership restrictions, and the immutable state of already-approved expenses. This is exactly the behavioral context an agent needs beyond the schema.

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?

Four sentences with no filler. The core action is front-loaded ('Update an expense'), followed by the most critical constraints in logical order. Every sentence adds a necessary piece of 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?

While the description covers permissions and status side effects well, it does not address partial-update semantics, error behavior when permissions are insufficient, or whether an approver can modify an already-approved expense. With no output schema and minimal annotations, these gaps leave some uncertainty for an agent invoking the tool.

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 only 38%, so the description must compensate for undocumented parameters. It adds real meaning only for 'status' by explaining the workflow implications of each value; the remaining seven parameters (date, amount, expense_id, project_id, description, is_billable, activity_type_id) receive no semantic guidance beyond their names.

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?

Description states a clear verb and resource ('Update an expense') and adds distinctive behavior around status transitions and ownership permissions. It implicitly differentiates from siblings like timelog_add_expense and timelog_approve_expense by describing the approval workflow, though it never names alternatives explicitly.

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?

Provides explicit contextual rules: owners can only touch their own expenses, 'time.approve' or full data scope expands access, and status transitions have specific authorization requirements. It also gives a clear exclusion ('An already APPROVED expense cannot be edited by its owner'), but does not explicitly route the agent to timelog_approve_expense for the approval action.

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