Evaluate decoded hardware events against a contract's timing assertions (when/require/within, forbid/while/before) to return pass, marginal, or fail verdicts.
Judge decoded hardware events against an events contract's temporal assertions (when/require/within, forbid/while/before). Events: [{source, type, start_ns, end_ns, fields}].
| Name | Required | Description | Default |
|---|---|---|---|
| events | Yes | ||
| contract_path | Yes |
Changes observed during successful MCP inspections.
v0.6.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the assertion kinds checked (when/require/within, forbid/while/before) and the event record shape. However, it says nothing about the outcome semantics: what happens on a violation, whether it is a pure read/verdict operation, or what permissions the contract file requires.
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 dense sentences with the action front-loaded and no filler; the assertion list and event shape are packed into parentheticals efficiently. Slightly cryptic for readers unfamiliar with the assertion vocabulary.
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?
No output schema and no annotations mean the description should say more about the verdict/return shape and error behavior, which it does not. The input side is reasonably covered, but an agent calling this cannot predict what a result looks like.
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 description coverage is 0%, so the description's inline expansion of the events array (source, type, start_ns, end_ns, fields) is genuinely valuable and compensates for the empty items schema. It leaves contract_path completely unexplained, so the compensation is only partial.
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 (judge) and resource (decoded hardware events) and adds the contract's temporal assertion vocabulary, which pins down the operation precisely. It is distinguishable from judge_contract by scope (events vs. the contract itself), though it never explicitly contrasts the two.
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?
There is no explicit when-to-use guidance, no prerequisites, and no named alternative among the siblings (judge_contract, list_contracts). The phrase 'decoded hardware events' hints at a pipeline stage, but the agent must infer when this tool is the right choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.