aiworkhub_environment_preflight

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

Annotations already declare readOnlyHint=true and the description agrees ('READ-ONLY'), so no contradiction. It adds real behavioral semantics beyond annotations: provider access is only 'observed' when an adapter bridge or credential source proves it, and bare installed binaries stay 'installed_unverified_access' — a trust/falsifiability rule an agent could not infer otherwise.

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 purpose and the unverified-access rule are front-loaded and earn their place, but the bulk is a single dense, backtick-laden sentence enumerating output folding that the tool already exposes via an output schema. It reads as implementation documentation rather than call guidance, making it hard to scan.

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?

With annotations covering safety, an output schema covering returns, and only two optional parameters, the description is close to sufficient for correct invocation. What it omits is the selection context — why an agent would call preflight rather than a specific subsystem health tool — and it spends its length re-describing returns instead.

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 0%, so the description must carry the load and largely does: it explains that 'summary' is the default, that it folds specific sub-blocks into counts/identity, and that 'evidence' is equivalent to 'full' and returns repo_policy.build_preflight unchanged. It also explains that passing adapter_id filters providers and provider_observability to that adapter. Only the handling of an unknown adapter_id is left unstated.

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 opening line names the resource set precisely: unified readiness for repository, policy, Source Graph, and providers. The 'preflight' framing plus 'READ-ONLY' makes the read/aggregate nature clear. It does not differentiate itself from nearby readiness siblings (dashboard_health, source_graph_health, cli_adapter_report_readonly), so it stops short of a 5.

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 through the default: use 'summary' unless you need the exact build_preflight payload, in which case use 'evidence'/'full'. There is no guidance on when to run this preflight versus the many per-subsystem health/report siblings, and no stated prerequisites or when-not-to-use conditions.

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