Outcome-feedback (learning loop). Record what ACTUALLY happened to a previously-assessed product as a labeled calibration case; the weekly recalibration folds it into the gate. Operator-only (requires operator_key). Provide either job_id (links the case to that assessment + reuses its product) or product text.
| Name | Required | Description | Default |
|---|---|---|---|
| notes | No | ||
| job_id | No | ||
| product | No | ||
| operator_key | Yes | ||
| year_observed | No | ||
| actual_outcome | Yes | ||
| expected_verdict | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Describes the action as recording a calibration case, which implies a write operation. Notes operator-only access, but without annotations, the description carries full burden; it does not detail side effects or system impact beyond the weekly recalibration mention.
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?
Three sentences with key information front-loaded. Every sentence adds value: purpose, access restriction, and parameter guidance. No redundancy or fluff.
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?
Covers core purpose, access, and parameter selection logic. Lacks explanation for enum values, optional parameters (notes, year_observed), and return behavior. Without output schema, the description should provide more on what happens after recording.
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?
With 0% schema coverage, the description adds significant meaning: explains job_id vs product, operator_key restriction, and implicitly covers actual_outcome and expected_verdict. However, enum values remain unexplained and notes/year_observed are omitted.
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 tool's function: recording actual outcomes for calibration cases. It uses a specific verb ('record') and resource ('outcome') and distinguishes from siblings by focusing on feedback rather than assessment.
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?
Explicitly states precondition (operator-only, operator_key required) and parameter selection (job_id or product text). Implicitly indicates when to use (after assessment) but lacks negative guidance or alternatives.
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.