inspect_document

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states 'Build a high-level summary' without mentioning any side effects, error cases, handling of size limits (max_size_bytes), or truncation behavior. The absence of any caveats or return behavior details leaves the agent under-informed for a tool with multiple configurable parameters.

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 sentence that is front-loaded and easy to parse. It avoids unnecessary words and gets straight to the point. However, it may be too sparse given the tool's complexity, but as a concise statement it is effective.

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 5 optional parameters and an output schema, but the description provides minimal context. It does not explain what 'summary' entails, how the tool behaves when both html and document_handle are provided, what happens on size limits, or the relationship to sibling parse tools. This is incomplete for a tool that can operate in two different modes with configurable limits.

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 0%, so the description must compensate. It maps 'stored HTML' to document_handle and 'inline HTML snippet' to html, adding some meaning for those two parameters. However, it ignores max_size_bytes and truncate_on_limit, which are completely unexplained. The description does not fully compensate for the schema's lack of parameter documentation.

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 the specific verb 'Build' with a clear resource ('high-level summary') and scope ('stored HTML or an inline HTML snippet'). It distinguishes itself from sibling tools like parse_html_document or query_selector by focusing on summarization rather than extraction or parsing, though it doesn't explicitly name them.

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 implies usage for high-level summarization of HTML content but provides no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives or edge cases (e.g., when to choose parse_html_document instead). It only offers a brief context of the two input modes, which is insufficient for tool selection.

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