Change an expense: date, vendor, category, amount, tax, receipt photo or note. Amounts are still typed by a worker. The worker who entered it, the owner or office can change it.
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| vendor | No | ||
| category | No | ||
| spent_on | No | ||
| tax_minor | No | Tax part of amount_minor, typed by the worker. Default 0. | |
| expense_id | Yes | ||
| amount_minor | No | Total paid in cents, typed by the worker from the receipt. | |
| receipt_media_id | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full disclosure burden. It usefully clarifies the authorization model and that amounts are human-typed rather than recalculated, but it omits partial-update semantics (only expense_id is required, implying a patch-style update), what happens on an unknown/closed expense, and whether changes are audited or reversible.
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 short sentences with the field list front-loaded and no filler. The closing permission sentence is the only slightly redundant element, since it restates actor types in two forms.
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 an 8-parameter mutation tool with no annotations and no output schema, the description covers the field surface and permissions but leaves the agent guessing about patch-vs-replace behavior and failure/edge cases. Adequate, but not sufficient for a write operation of this size.
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%, but the description enumerates every mutation target — date, vendor, category, amount, tax, receipt photo, note — which maps onto spent_on, vendor, category, amount_minor, tax_minor, receipt_media_id and note, effectively compensating for the undocumented fields. It still omits formats and units (ISO date, minor/cents units), so not a 5.
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 ("Change") plus the resource ("an expense") and enumerates the mutable fields, so the CRUD intent is unmistakable. It does not name its siblings (expenses_add / expenses_remove / expenses_list) to draw the boundary explicitly, which keeps it from a 5.
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 only implied — an existing expense identified by expense_id gets modified. The description does add a useful permission rule ("the worker who entered it, the owner or office can change it"), but it never states when to use this versus expenses_remove for deletion or expenses_add for new records.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.