infra_summary

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

Annotations already indicate readOnlyHint, idempotentHint, and destructiveHint=false, so the description need not cover safety. It adds value by specifying the summary contents, which is beyond the annotations. However, it doesn't disclose whether the counts are live or cached, the scope of the scan, or any performance characteristics.

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, dense sentence that front-loads the primary content (counts by kind/relationship) and then lists additional metrics. No superfluous wording.

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 zero-parameter, read-only summary tool with rich annotations, the description is adequate but lacks details on scope (e.g., entire subscription? all subscriptions?) and output format. Without an output schema, it should specify what exact fields are returned, not just a list of concepts. Missing guidance on how it fits into the broader toolset reduces completeness.

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?

With zero parameters, the baseline is 4. The description correctly implies no input is required, aligning with the empty schema.

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 clearly states the resource being counted ('resource kind and relationship') and lists the specific summary metrics it returns (scan time, subscriptions, unattached NSGs, public IPs). It distinguishes itself from siblings like scan_infrastructure or find_resource by being a summary tool, though it doesn't explicitly name an alternative.

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?

There is no guidance on when to use this summary versus drilling into specific resources via the many sibling tools (e.g., scan_infrastructure, find_resource). An agent must infer that this is an initial overview, but the description provides no explicit when-to-use or when-not-to-use instructions.

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