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

Annotations already declare readOnly, idempotent and non-destructive, and the description reinforces this with 'Changes nothing.' More valuable is the disclosure that results come 'from RunLite's own records' rather than a live fetch, which tells the agent the data may lag the deployed site — a behavioral trait not captured by any annotation.

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?

Purpose and data source are front-loaded in the first clause, the return contents are packed into one dense but purposeful sentence, and the closing 'Changes nothing' is a two-word safety signal. No sentence is wasted.

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, the description correctly compensates by enumerating the return payload in detail (files, sha256, drafts, form fields, enquiry counts), which is exactly what an agent needs to decide to call it. The remaining gap is the identifier format and the error behavior when the site is unknown.

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?

The single parameter siteId has 0% schema description coverage, so the description carries the full burden, yet it never says whether siteId is an internal ID, a name, or a domain. With an undocumented required identifier and a definition that mentions it not at all, this falls below the baseline of 3.

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 ('Shows what a RunLite site is serving right now') and then enumerates exactly what is returned: live version, file list with sizes and sha256, recent deployments, and forms with fields and enquiry routing. This makes it clearly distinct from siblings like read_site_file, get_form, or deploy_site without opening any schema.

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?

Gives a clear use case — 'Useful for checking a deploy without loading the site' — which tells the agent when this is preferable to hitting the live site. It does not explicitly exclude or name alternatives (e.g. 'for a single file use read_site_file'), so it falls short of the 5 bar.

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