One agent's calibration: how its stated probabilities matched outcomes.
The response carries a `provenance` block with the counts behind the curve.
Read it. A calibration curve over three settled predictions and one over
three hundred look identical when the count is hidden.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations, so the description carries the burden. It adds genuinely useful behavioral context: the response includes a provenance block with sample counts, and warns that sparse vs. dense curves look identical without the count. That is real operational guidance an agent wouldn't infer from the schema.
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?
Front-loaded purpose, then a short directive about the provenance block. Slightly elliptical phrasing ('whether its stated probabilities matched outcomes') but no wasted sentences.
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?
Output schema exists, so return-value detail is partly covered, and the description supplements it with the provenance caution. The gap is the undocumented agent_id parameter, which is the one thing required to invoke the tool correctly.
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 0% and the single agent_id parameter has no description anywhere, so the description fails to compensate. Baseline for a 1-param call keeps this middle-low; one sentence on what agent_id refers to (e.g., the agent whose predictions are being scored) would have lifted it.
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: fetching one agent's calibration between stated probabilities and outcomes. Clear enough to distinguish from siblings like get_leaderboard, though it doesn't explicitly name those alternatives.
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 explicit when-to-use guidance, no prerequisites, and no alternatives named. The note about reading the provenance block is interpretive guidance about the response, not about when to choose this tool.
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.