Prove an outcome by asserting page text, URL, or visible references, then return pass/fail for reliable verification.
Prove an outcome instead of inferring it. Provide one of: contains (page text includes string), url_includes (current url contains string), ref_visible (a ref is present and visible). Returns pass/fail.
| Name | Required | Description | Default |
|---|---|---|---|
| tabId | No | ||
| contains | No | ||
| ref_visible | No | ||
| url_includes | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It explains what each assertion does and states that the tool returns pass/fail, which covers the core behavior. But it does not disclose side effects, what a 'ref' refers to, how tabId affects the current tab, or behavior if multiple modes are provided.
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?
Three tight sentences: a purpose statement, a compact list of modes with inline explanations, and a return-type note. No filler, and the key usage rule is front-loaded.
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?
The description is adequate for a simple assertion tool: it names the modes and the pass/fail return value. It falls short on operational details an agent would need, such as what 'ref' means, whether tabId is required, and what happens when assertions fail (exception vs. false).
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 0%, so the description must compensate. It adds meaningful semantics for contains, url_includes, and ref_visible, and clarifies that they are alternatives. However, tabId is left unexplained, and the 'provide one of' rule is not enforced in the schema.
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 job: prove an outcome rather than infer it, and lists three concrete assertion types (contains, url_includes, ref_visible). This is a specific verb plus resource, and the contrast with 'inferring' hints at the sibling browser_observe, though no sibling is named explicitly.
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 'Prove an outcome instead of inferring it' gives clear context for when to use this tool rather than an observational tool like browser_observe. 'Provide one of' also instructs the agent to supply exactly one assertion mode. However, it does not explicitly mention alternatives or discuss when not to use the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.