utility_defect_preflightFind false-green risk by linting utility audit claims against evidence, freshness, and external-receipt requirements; returns a signed Corbelworks action receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| manifest | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | Yes | ||
| preflight | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds behavioral context by naming the linting dimensions (evidence, freshness, external-receipt requirements) and the side effect of returning a signed receipt, which goes beyond the bare annotation.
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?
The description is a single sentence, front-loaded with the core action ('Find false-green risk'), contains no filler, and efficiently incorporates both the method (linting claims) and the output (signed receipt).
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?
Because an output schema exists, return-value details are covered. The description captures the tool's purpose and distinctive preflight role. It falls slightly short on explicit relationship to siblings and on clarifying the nested 'manifest' input structure, which is not explained in the schema either.
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 must compensate. It partially does by identifying 'utility audit claims' as the subject and mentioning linting requirements, which gives meaning to the 'claims' array. However, the 'manifest' parameter and nested claim structure remain unexplained, limiting the compensation.
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 opens with 'Find false-green risk by linting utility audit claims' – a specific verb and object. It also distinguishes from siblings 'purchase_utility_defect_scan' and 'verify_action_receipt' by positioning this tool as a preflight linting step, not the purchase or verification action.
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 term 'preflight' implies it should be used before the actual scan or purchase, but the description provides no explicit when-to-use or when-not-to-use guidance, nor does it name alternatives. Usage is only implied, not clarified.
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.
Each tool has a clearly distinct purpose: triaging permit/inspection rows, purchasing a defect scan, preflighting utility claims, and verifying receipts. No overlap or ambiguity in their roles.
Tool names are predominantly snake_case with verb_noun structure (purchase_utility_defect_scan, verify_action_receipt), but one name (permit_inspection_exception_watchlist) is a compound noun rather than verb-led. Minor deviation from an otherwise consistent pattern.
With 4 tools, the server is tightly scoped to its reliability niche. Each tool addresses a specific step or concern, and the count feels neither sparse nor bloated.
The tools cover a clear workflow (preflight, purchase, verify), and the watchlist addresses a distinct concern. Minor gap: there is no tool to actually execute the defect scan or retrieve results, but the purchase link may serve that purpose externally.