preview_reference_company_onboarding

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false; the description complements this with the domain-specific guarantee that it validates 'without granting authority,' which clarifies the absence of provisioning or authorization side effects. This adds meaningful context beyond the annotations, though it could further explain what validation entails (connectivity, blueprint compliance, etc.).

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?

A single nine-word sentence with no filler. The verb is front-loaded and the key scoping clause ('without granting authority') comes at the end with every word earning its place.

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 five parameters (including a six-field nested connector_selections object) and 0% parameter documentation, nine words are insufficient. The output schema and annotations cover return shape and safety, but the description fails to explain the validation semantics, the meaning of the refs, or where this tool sits relative to readiness and deployment siblings such as get_reference_company_onboarding_readiness.

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 carries the burden, but it only loosely echoes the parameter names: 'connector and harness choices' maps to connector_selections and coding_harness. It provides no semantics for company_ref, project_ref, or blueprint_version_ref, and no guidance on how connector_selections must relate to the blueprint, leaving the agent to rely solely on regex patterns and field names.

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 uses a specific verb ('Validate') and identifies the resource ('exact connector and harness choices'), and the 'without granting authority' clause distinguishes it from tools that would actually provision or deploy. It stops short of a 5 because it doesn't explicitly differentiate from the closest sibling (get_reference_company_onboarding_readiness) or clarify what criteria the validation checks.

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?

No explicit when-to-use condition or named alternative is provided. The 'without granting authority' phrase implies this is the non-destructive validation step, but the agent is left to infer the workflow and cannot easily distinguish this tool from get_reference_company_onboarding_readiness or provisioning siblings like company_provisioning and company_bring_up.

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