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

Goes well beyond the annotations by disclosing the full execution pipeline (recompile contract, hash artifacts, run each criterion, return APPROVED or QUARANTINED with per-check evidence and a tamper-evident pack hash) and, critically, that this MCP call is a free discovery call that does not execute the capability or charge. That free-vs-paid distinction is the single most decision-relevant fact for an agent and is stated unambiguously, consistent with readOnlyHint/idempotentHint.

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?

Four dense sentences, front-loaded with the purpose and then the capability/limit disclosure, with no filler. The exclusion list is a bit long but each item guards against a plausible misinterpretation of 'verification'. The dual framing (advertised capability vs. actual discovery response) takes a re-read to fully parse.

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?

Given an output schema exists, return values need not be spelled out, yet the description still covers outcomes and the free-discovery caveat, so an agent knows what to expect. The only shortfall is that it never situates itself relative to the sibling verify_execution, leaving ambiguity about which verification entry point to call.

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 100%, so the baseline is 3, but the description adds real meaning by explaining that every supplied artifact gets hashed and that the supported criterion families map to JSON Schema, exact-value, required/forbidden-text and SHA-256 checks — which clarifies the acceptanceCriteria enum values and why artifacts must be named. It does not explain artifact naming alignment between contract criteria and the artifacts array, which is the main remaining semantic gap.

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?

Names a specific verb (verify) and resource (AI agent work delivery against acceptance criteria) and identifies the upstream producer, job_contract_compile, so the agent understands the contract flows in from there. It is clear about what is verified and what the call actually returns (x402 endpoint, price, payment guide), but never distinguishes itself from the sibling verify_execution, which an agent could easily confuse with this one.

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?

Gives concrete usage context: feed it the objective contract produced by job_contract_compile, along with the artifacts the criteria reference. It also states scope exclusions (not an authorship detector, malware scan, factuality certificate or legal opinion), which helps rule out misuse. It stops short of naming an explicit alternative or when-not-to-use condition versus verify_execution.

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