Audit infrastructure

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

No annotations are provided, so the description carries the full burden. It does disclose the safety-critical 'Read-only' property and sketches the return shape (score, counts, top findings). It says nothing about permissions required, cost/rate of running a full estate audit, or whether the report is cached versus freshly computed.

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?

Three short sentences, front-loaded with the read-only guarantee and the core purpose, then the outputs, then the mode flags. Zero filler, though the mode sentence compresses two distinct invocation paths into one line.

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 no output schema and no annotations, the description does cover what the tool returns (score, counts, top findings) and the principal invocation modes. It leaves refresh and demo semantics undocumented, but an agent could still call the tool correctly in its default form.

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 83%, so the schema already documents most parameters, and the description largely restates finding=N and full=true. It does add the useful interplay between the summary, full-report and single-finding modes, but notably omits top, page, demo and refresh.

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 and resource ('Audits every configured Hetzner project') plus the audit domains (security, cost, reliability, hygiene). It is clearly distinguishable from the sibling list/create/delete tools, none of which perform portfolio-wide auditing.

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?

It explains mode selection within the tool (finding=N for one fix, full=true for the whole report), which helps invocation. However, it gives no guidance on when to reach for this audit versus related siblings like spend_history, find_capacity or infra_map.

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