Stage a receipt or expense document for review and chat confirmation before uploading. Attach it to an existing expense, or let it create a parsed expense draft.
Prepare a staged file for review and chat confirmation. No upload yet. expenseId attaches to an existing expense; otherwise upload creates a parsed expense draft.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| fileId | Yes | ||
| expenseId | No | ||
| requestKey | Yes |
Changes observed during successful MCP inspections.
v0.1.5Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is partly covered. The description usefully adds that nothing is uploaded yet and that expenseId changes whether an existing expense is attached or a new draft is parsed, but it does not describe idempotency, permissions, or what the staged artifact looks like.
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?
Two compact sentences, front-loaded with the core action and the 'no upload' caveat. The second clause is dense but every word carries information; no padding.
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?
With no output schema and zero annotation-level detail on returns, the description covers the primary branching behavior but leaves gaps on what 'staged' produces, how requestKey is used, and how the confirmation step is triggered. Adequate but not complete for a 4-param staging 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 0% for 4 parameters, so the schema carries no meaning at all. The description explains only the optional expenseId semantics (attach to existing expense vs. create a parsed draft); requestKey (likely idempotency), fileId, and title remain undocumented.
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+resource (prepare a staged file) and explicitly scopes it with 'No upload yet', which separates it from a real upload/execute step. It does not, however, distinguish itself from the close sibling stage_expense_file, leaving the agent to infer which staging tool applies.
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?
'For review and chat confirmation' implies this is the first step of a two-phase flow, but no sibling is named and no explicit when-to-use / when-not-to-use guidance is given. The expenseId sentence describes a branch condition rather than when to pick this tool over stage_expense_file or execute_draft.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.