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

Annotations already declare this a mutating, destructive, idempotent operation; the description adds value beyond that by disclosing that a supplied split replaces the entire previous split, that changing an equal/percentage amount preserves people and proportions, and that owner/editor authorization is required. It stops short of describing the response or failure behavior for a tool with no output 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 tightly packed sentences with the action and mutable fields front-loaded; no filler. It is dense but every clause carries operational meaning (ID sourcing, partial update, split replacement, permissions).

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 10-parameter mutation with no output schema, the description covers the essentials an agent needs: where IDs come from, that only changed fields should be sent, split replacement semantics, and authorization. It omits error/validation behavior (e.g., split sums must match amount) and any statement about what the update returns, which are minor given the schema's enum and split constraints.

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 high (80%) and the nested split object is already well documented in the schema, so the baseline is 3. The description still earns credit for semantics not in the schema: 'a split replaces the whole split', the proportion-preserving rule when the amount changes, and a concrete 100%-one-person example.

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?

Opens with a specific verb+resource ('Change an existing trip expense') and enumerates the mutable fields (amount, description, date, category, payer, split). This cleanly separates it from sibling trip_expense_create and trip_expenses_list, which the description also names as the ID source.

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?

Gives concrete prerequisites (expense ID and traveler IDs come from trip_expenses_list), a permission constraint (only owner or editor), and the partial-update rule ('send only the fields that change'). It does not state when to prefer this over a delete-and-recreate or how it relates to trip_expense_create, but the operational context is clear.

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