save_html

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, and an output schema exists, so the safety profile and return shape are covered elsewhere. The description adds one useful behavioral fact (the entire page HTML, not a fragment / selector subset) but omits whether an existing file is overwritten, what the output dir actually resolves to, and whether the browser must be navigated to a page first. Note a mild tension: the tool persists a file to disk while annotations claim readOnlyHint=true — consistent with sibling export tools treating file emission as non-mutating, but worth flagging.

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 front-loaded sentence with zero filler and the destination stated up front. It is efficient rather than padded, though its brevity edges into under-specification rather than tightness.

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?

The tool is structurally simple (one optional param, output schema present), so the description is nearly sufficient to call it. It still leaves gaps an agent must resolve elsewhere: what "output dir" means in this server's configuration, overwrite behavior, and how the saved file is reported back.

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?

There is one parameter (filename, defaulting to page.html) and schema description coverage is 0%, so the description is the only place semantics could be supplied — yet it never mentions the filename parameter or its default. An agent must open the schema to learn it can rename the artifact or that omitting the argument yields page.html.

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?

"Save the full page HTML to the output dir" names a specific verb (save) and resource (full page HTML) plus a destination, so the action is unambiguous. It does not, however, distinguish itself from the sibling get_html (which presumably returns markup inline) or save_pdf/screenshot_file, leaving the save-vs-retrieve distinction to the reader's inference from the name.

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?

No when-to-use guidance, no prerequisites, and no named alternatives. The only implied usage cue is the phrase "to the output dir," which hints at persistence, but nothing tells an agent to prefer this over get_html when it just needs the markup in context.

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