scan_infrastructure

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

Beyond the annotations' readOnly/idempotent/openWorld profile, it discloses concrete operational requirements: DefaultAzureCredential sourcing (az login, managed identity, env vars) and Reader permission level, plus the downstream consequence that skipping enrich leaves certain verdicts 'unknown'. This is meaningful context an agent cannot get from structured fields.

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?

Opening line gives the action and scope, followed by tightly grouped auth requirements and per-parameter notes. Every sentence adds information; no filler or repetition of the schema.

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?

No output schema exists, and the description covers the operation, auth, permissions, and both parameters adequately. It does not say what the tool returns or how to confirm the rebuild succeeded, which is the main remaining gap for a heavyweight ingestion 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 0%, so the description carries the full burden, and it does: subscription_ids ('limit the scan; omit to scan every enabled subscription visible') and enrich (child settings Resource Graph lacks, with the specific resource types listed). Both parameters are fully explained with defaults and consequences.

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?

States a specific verb (scan/rebuild) and enumerates exactly what is ingested: resources, resource groups, RBAC role assignments, and access settings. This scope enumeration clearly separates it from the read-only query siblings like find_resource or who_has_access.

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 explains the effect of both parameters ('omit to scan every enabled subscription', enrich adds child settings), which implies usage, but never states when to run this versus the many sibling query tools, nor when not to run a full scan. Usage is inferred rather than prescribed.

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