inspect

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

With no annotations, the description carries full responsibility for behavior. It does disclose a key trait ('without vision') and a timing behavior (re-resolve after re-render) plus a partial return shape ({found, tag, te…). However, it does not mention side effects, failure modes, or behavior for geometry/relation kinds, so transparency is incomplete.

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 given text is concise and front-loaded with the core purpose. However, it clearly appears truncated mid-word ('te…'), which disrupts structure and completeness. A definition that ends abruptly cannot be fully evaluable as a polished, complete tool description.

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?

This tool has five parameters, a three-value enum, no output schema, and no annotations—so the description must compensate heavily. It only details the 'element' kind, omits geometry/relation behavior, and provides no return-format explanation beyond a fragment. The description is too incomplete for an agent to know how to call this tool for all advertised kinds, making contextual completeness inadequate.

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 60%, so the schema documents kind, refA, and refB. The tool description adds meaning for the ref parameter in the element context (checking liveness, re-resolve after re-render) and illustrates the kind enum. But it does not explain selector or the geometry/relation parameter interactions at all, leaving some of the parameter space under-explained.

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 opens with 'Element introspection without vision', which states a specific action on a specific resource and distinguishes it from visual tools like screenshot. It further clarifies the element kind by showing an example outcome (is ref alive? re-resolve after re-render → {found,tag,te…), though it only elaborates on the 'element' kind and is truncated. Overall, the core purpose is clear, but it could better differentiate among the three kinds (element, geometry, relation).

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 phrase 'without vision' implies when to use this tool—when you need DOM/ref introspection rather than a screenshot—but it does not explicitly name alternatives or state when not to use it. The element example (re-resolve after re-render) gives a concrete use case. No direct comparison to sibling tools like evaluate or explore_page is provided, leaving 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.