read_html

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It does state the tool 'Read/analyze existing HTML file,' implying a non-destructive operation, and offers insight into text mode with offset/limit progressive reading. However, it does not disclose the return format, the behavior of the other modes (structure, content, compressed), or any potential errors or side effects. This is a partial disclosure but not comprehensive.

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?

The description is a single concise sentence that pairs a clear purpose with a valuable usage hint. It is front-loaded with the core function ('Read/analyze existing HTML file') and immediately follows with actionable mode guidance. There is no redundant information or filler.

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 has no output schema, so the description should explain what the tool returns or how the different modes behave. It does convey the basic read/analyze function and hints at text mode's efficiency, but it omits return value details and the behavior of the other three modes. Given the tool's moderate complexity (4 parameters, enum), the description is adequate but incomplete without further elaboration.

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 50% (limit and offset have descriptions). The description adds value by explaining that mode='text' is token-efficient and that offset/limit are used for progressive reading in text mode. However, it does not clarify the meaning of 'file_path' (though self-evident) or the semantics of the other mode values (structure, content, compressed). Thus it partially compensates for the schema's gaps but does not fully elaborate on all parameters.

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 uses a specific verb+resource combination: 'Read/analyze existing HTML file.' This clearly identifies the tool as a reading/analysis operation on HTML files, distinctly separating it from the sibling tools which are all editing, writing, or rendering operations (e.g., patch_html, write_html_file, preview_html). The emphasis on 'existing' further reinforces its read-only nature.

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?

The description provides clear usage context by recommending 'Use mode='text' for token-efficient plain text extraction with offset/limit progressive reading.' This gives actionable guidance on parameter selection. While it does not explicitly name alternatives or state when not to use the tool, the sibling context (all write/edit tools) makes the read-oriented use case obvious. The lack of explicit exclusions is a minor gap.

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