web_extract

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

With no annotations, the description must carry behavioral disclosure. It only says 'scrapes structured data,' omitting whether the operation is read-only, modifies page state, or requires specific conditions. The agent cannot infer side effects or dependencies.

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 short sentence, which is concise but lacks additional context such as output format or usage note. It earns its place but could be more helpful without much bloat.

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?

For a tool with no parameters, no output schema, and no annotations, the description is insufficient. The term 'structured data' is vague, and the agent is left guessing about the return format or any constraints. More completeness is needed to set expectations.

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 tool has zero parameters, and schema coverage is 100%. The description adds no parameter detail, but the baseline is 4 for no parameters, as parameter documentation is not needed.

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 clearly states the tool scrapes structured data from the current page, using a specific verb ('scrapes') and resource ('current page'). Among siblings like web_read and web_find, this distinguishes it as a structured extraction tool.

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 guidance on when to use this tool over alternatives. The agent receives no context about prerequisites (e.g., page must be loaded) or when to choose web_extract instead of web_read or web_find.

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