mcp-electron-driver

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 effectively describes key behaviors: the snapshot is based on the 'accessibility-tree,' it generates 'numbered refs' for interactive elements, and these refs are reusable across tools like click and type. However, it lacks details on potential limitations (e.g., performance impact, page state changes) or error handling, which prevents a perfect score.

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 appropriately sized and front-loaded: the first sentence states the core purpose, followed by key benefits and usage instructions. Every sentence adds value, such as explaining ref usage and when to call the tool, with no redundant information. It efficiently conveys necessary details without verbosity.

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?

Given the tool's complexity (interaction with web pages) and lack of annotations or output schema, the description is largely complete. It explains what the tool does, how to use it, and its integration with sibling tools. However, it does not detail the output format (e.g., structure of the text representation) or error cases, which could be helpful for an agent, slightly reducing completeness.

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 input schema has 100% description coverage, with the single parameter 'selector' documented as 'Optional root selector. If given, only snapshot that subtree.' The description does not add any meaningful semantics beyond this, as it focuses on the tool's overall function rather than parameter details. According to the rules, with high schema coverage, the baseline is 3 when no extra param info is provided.

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's purpose: 'Return a structured text representation of the visible page with numbered refs.' It specifies the verb ('Return'), resource ('structured text representation'), and distinguishes from siblings by explaining that refs can be used with other tools like click and type instead of selectors. The mention of 'accessibility-tree-based representation similar to Playwright MCP's browser_snapshot' further clarifies its 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 explicit usage guidance: 'Call this FIRST before interacting with a page to see what is on screen.' It distinguishes from alternatives by noting that refs eliminate 'selector-guessing round-trips' and implies when not to use it (e.g., after initial snapshot, use other tools with refs). This directly addresses when to use this tool versus others in the sibling list.

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