Call a WebMCP tool

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds genuinely new and important context that the return value originates from the website and is untrusted, with an explicit instruction not to follow embedded instructions — critical prompt-injection guidance for an open-world, non-read-only call. It stops short of covering failure modes or what happens when the named tool is absent from the target frame.

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 sentences, zero waste, and the most safety-critical fact (untrusted output) is placed immediately after the action statement rather than buried. Nothing here is padded or 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?

For a 5-parameter tool with a nested free-form input object and no output schema, the description covers the action and the trust boundary — the two things an agent most needs. It does omit any indication of what the return value looks like or how failures surface, which matters more here because no output schema exists.

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 100%, so all five parameters (name, input, tabId, frameUrl, timeoutMs) are already fully documented in the schema, including defaults and disambiguation logic. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

"Calls a WebMCP tool exposed by the page with the given input and returns its output" gives a specific verb (calls) and resource (page-exposed WebMCP tool), which separates it from the sibling webmcp_list that enumerates rather than invokes. It is clear and unambiguous, though the sibling relationship is only implied by wording rather than stated.

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?

Usage is implied: you must already know a tool name, and the schema's "Tool name from webmcp_list" hints at a discovery-then-call flow. But the description itself never says when to use this versus webmcp_list, nor any prerequisites (e.g. WebMCP availability, tab selection) or exclusions.

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