chrome_call_site_tool

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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, so the agent knows this is an unsafe, side-effecting call into page-supplied code. The description adds the mechanism (page-declared tools) but says nothing about trust boundaries, failure modes, or that the invoked behavior is entirely page-controlled. Adds some context; not rich.

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?

Two short sentences, front-loaded with the purpose and followed by the prerequisite action. Nothing redundant.

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?

There is no output schema, and for an open-world, destructive tool that proxies arbitrary page-declared APIs the description never indicates what is returned or how errors from the page tool surface. The snapshot prerequisite is covered, but return/error behavior is left entirely implicit.

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 coverage is 60%; tabId, frameId and snapshotId are documented in the schema, but the required toolName and the free-form nested args object are undocumented anywhere. The description only indirectly supports snapshotId via the snapshot-first instruction and adds no syntax for args, so it does not compensate for the coverage gap.

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?

States a specific verb (invoke) and resource (a tool the web page itself declares), and names the concrete declaration surfaces (window.mcp / window.__mcp_tools__ / meta[name=webmcp-tool]). This clearly separates it from browser_evaluate or chrome_evaluate, which run agent-supplied code rather than page-declared tools.

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?

Gives an explicit prerequisite in 'Take a chrome_snapshot first to see the catalog,' routing the agent to the sibling that produces the toolName/snapshotId it needs. No when-not guidance or statement about what to do if the page declares no tools.

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