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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds value beyond that: it discloses that content is draft-state, versioned, and that the batch form is capped at 40 files — a hard limit nowhere in the schema or annotations.

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, no filler, with the core purpose first, the workflow rule second, and the batch constraint last. Every sentence carries information the agent can act on.

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 zero required parameters and no output schema, the description should clarify invocation shape (path vs paths, whether id is needed) and at least hint at the return payload (file contents, line ranges). It covers the batch cap but leaves the required-parameter story and return format unstated.

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 80%, so the baseline is 3; the description clears that bar slightly by stating the concrete 40-file cap for `paths`, which the schema only calls 'Several files at once.' It does not explain the relationship between `path` and `paths` (alternatives?) or whether `id` is effectively mandatory despite nothing being required.

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 (read) and resource (draft files of an HTML-first site), plus a versioning nuance. It is distinguishable from write_site_file / edit_site_files by the read verb and 'draft' qualifier, but never explicitly contrasts with list_site_files or search_site_files, which an agent could plausibly confuse it with.

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?

'Read before you edit' gives a real workflow cue that establishes ordering relative to edit_site_file/write_site_file. However, it names no alternatives and gives no when-not conditions (e.g. use search_site_files to locate a path, list_site_files to enumerate), leaving sibling selection partly to inference.

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