judge_contract

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses that no hardware is touched (offline/replay operation) and lists the four output verdicts, which is meaningful beyond the schema. It says nothing about error behavior when the contract file is missing or malformed, or whether the verdicts are mutually exclusive per observation.

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 compact clauses with the outcome list front-loaded and the usage note appended; nothing is wasted. The arrow notation packs the return contract into a few tokens, though the second clause is slightly clipped in phrasing.

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?

There is no output schema and no annotations, so the description must carry everything, and it does not. The verdict vocabulary is covered, but the input contract (contract file format, observation object shape) is completely unspecified for a tool whose entire correctness depends on those two inputs matching.

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% for two required parameters, so the description must compensate and does not. 'contract_path' is never clarified as a filesystem path or identifier, and the expected shape of 'observations' objects (timestamped samples? channel/value pairs?) is entirely unstated, leaving the agent to guess the input format.

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 names a specific verb ('Judge') and resource ('observations against a timing contract') and enumerates the four possible verdicts, so the agent knows exactly what comes out. It implicitly separates itself from hardware-capture siblings via 'No hardware', though it does not distinguish itself from judge_events or judge_serial, which look near-identical in shape.

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?

'use for replay or when an adapter already captured' gives a real condition for selecting this tool over the capture_*/check_* siblings. However, it never names an alternative explicitly and gives no guidance on when to prefer judge_events or judge_serial, which share the same judging verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.