Generate a calibration report that compares confidence buckets against observed accuracy from recorded outcomes, showing whether high-confidence answers are actually correct.
Calibration report: confidence buckets vs observed accuracy from recorded outcomes. Shows whether high-confidence answers are actually right that often.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does 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 implies a read-only report, but does not state whether it needs prior record_outcome data, what an empty/insufficient sample yields, or whether results are cached or permission-gated. Only the data source is disclosed.
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 short sentences, front-loaded with what the report contains, then a plain-language gloss on why it matters. The second sentence is mildly redundant but earns its place by translating the jargon.
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 zero-parameter stats tool with no output schema, the description should sketch the return shape (buckets, accuracy figures, sample sizes). It gestures at that but leaves the agent unsure what the report actually returns or requires as a precondition.
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 tool takes zero parameters, so there is no parameter meaning to add; baseline 4 applies. The description correctly does not invent inputs.
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 artifact (a calibration report pairing confidence buckets with observed accuracy) and its source (recorded outcomes). It is distinguishable from evaluate and record_outcome by content, though it never names those siblings explicitly.
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?
'from recorded outcomes' implies this is a downstream, read-only inspection step that only makes sense after outcomes exist, but there is no explicit when-to-use, no mention of the sibling tools, and no statement about what happens when no outcomes have been recorded.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.