Search Bill records by DocNumber (LIKE match).
Search Bill records by DocNumber (LIKE match).
| Name | Required | Description | Default |
|---|---|---|---|
| term | Yes | Search term matched against DocNumber with LIKE '%term%'. '%' is a wildcard; QBO does not support an ESCAPE clause. | |
| maxResults | No | Maximum number of results to return (default: 100, max: 1000) | |
| startPosition | No | Starting position for pagination (1-based, default: 1) |
Changes observed during successful MCP inspections.
v1.6.6Input schema / properties / term / descriptionPrevious value: -"Search term matched against DocNumber with LIKE '%term%'"New value: +"Search term matched against DocNumber with LIKE '%term%'. '%' is a wildcard; QBO does not support an ESCAPE clause."v1.4.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It discloses the LIKE-match behavior but says nothing about whether the search is case-sensitive, whether it spans all statuses (open/paid/voided), rate limits, or permission requirements. Minimal behavioral context for a read tool.
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?
One sentence, front-loaded with the verb and resource, zero waste. The parenthetical clarifies the match mode immediately.
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 3-param search tool with no output schema and no annotations, the description covers the match mechanism but omits result shape, pagination behavior (though schema covers it), and empty-result semantics. Functional but thin for a tool with zero structured behavioral metadata.
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 100% and the schema exhaustively documents 'term' including the '%' wildcard and ESCAPE limitation. The description reinforces the LIKE semantics, adding minor value over a schema that already does the heavy lifting. Baseline 3 is exceeded slightly by the explicit LIKE call-out.
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 (Search) and resource (Bill records) with the exact matching field (DocNumber). This clearly distinguishes it from qbo_bills_list (which lists without a search term) and from other *_search siblings.
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?
No guidance on when to use this search vs qbo_bills_list or qbo_bills_get, and no mention of the LIKE-only limitation as a routing consideration. The agent gets a purpose but no usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.