Update a preferred tool's margin or note to reflect user feedback on bias strength.
Change one preference's margin or note; only the fields you pass are changed. Use this when the user says the bias should be stronger or weaker ("actually, only use it when it's nearly as good").
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| margin | No | ||
| tool_id | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the burden of explaining side effects, permissions, or error handling. It only mentions that 'only the fields you pass are changed', which describes the partial-update behavior but does not address potential failure modes or consequences of omitting fields. The behavioral transparency is minimal.
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?
The description is concise, consisting of two sentences, and front-loads the primary action immediately. It avoids unnecessary verbiage and each sentence contributes directly to understanding the tool's purpose and usage.
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?
The tool has three parameters and a partial-update behavior, but the description does not explain parameter meanings or provide any context about expected outcomes, errors, or permissions. While the purpose and a use case are given, an agent would lack the information needed to invoke it correctly without additional domain knowledge.
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?
The schema has 0% description coverage, and the description fails to explain the meaning of 'margin' or 'note'. It only refers to them as fields to change, leaving their semantics ambiguous. The description does not compensate for the missing schema descriptions, so an agent would not understand what values to supply.
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?
The description clearly states the action ('change one preference's margin or note') and specifies the resource (preference) and the fields involved. It also provides a usage condition ('when the user says the bias should be stronger or weaker'), which helps distinguish it from other preference-related tools.
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?
The description explicitly tells when to use the tool: 'Use this when the user says the bias should be stronger or weaker'. It also adds a nuanced clarification ('actually, only use it when it's nearly as good') that narrows the scenario. However, it does not explicitly mention when not to use it or name alternative tools, so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.