oc_assert

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

Annotations already mark readOnlyHint=true and idempotentHint=true. The description adds behavioral details: returns verdict pass/fail/inconclusive, requires evidence else inconclusive, and mentions the core-tier vs pilot runtime distinction. No contradictions.

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 succinct sentences: first states purpose and outputs, second provides context about tool tier. No extraneous words.

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 tool with no output schema, the description adequately covers the return value (verdict and failed leaf assertions) and the required input condition (evidence). It also notes the tool's place in the architecture. Minor gap: does not explain the verdict options beyond pass/fail/inconclusive.

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 100%, so the schema already documents each parameter. The main description adds only marginal context (e.g., 'caller-supplied evidence (snapshot)'). Baseline score of 3 is appropriate.

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 verb 'evaluate', the resource 'Outcome Contract assertion', and the outputs (verdict and failed leaf assertions). It also distinguishes from sibling tools by noting this is the core-tier single-call surface, with retry/escalation elsewhere.

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?

The description implies usage context ('Core-tier single-call surface; retry and escalation live in the pilot runtime') but does not explicitly state when to use this tool vs alternatives or provide exclusion criteria.

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