Assert a condition against the current browser snapshot and return evidence. Supports checks for element existence, role, name, value, or text content.
Assert a condition against the current snapshot and return evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| uid | No | ||
| kind | Yes | ||
| expected | No |
Changes observed during successful MCP inspections.
v0.2.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation readOnlyHint=true already signals the tool is non-mutating, and the description aligns with that. The phrase 'return evidence' adds a small behavioral detail about the output, but the description does not explain what happens on failure (e.g., throw vs. return false) or what the evidence structure looks like, especially with no output schema.
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 a single, front-loaded sentence with no filler. It quickly communicates the core action and outcome without redundancies, achieving maximum conciseness while still being grammatical.
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 3 parameters, an enum of five condition kinds, and no output schema, this description is far too sparse. It fails to define what a 'snapshot' refers to, what kinds of conditions are supported, how expected is interpreted, or what evidence is returned. An agent would struggle to construct a correct invocation without seeing additional schemas or examples.
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 for parameter meaning. It does not mention uid, kind, or expected at all, nor explain how they combine for an assertion. The enum values are self-descriptive to some degree, but without guidance on the relationship between parameters, an agent cannot reliably know how to set expected or understand the role of uid.
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 specifies a verb ('assert') and resource ('condition against the current snapshot') and mentions returning evidence. It gives a general sense of a verification tool but does not enumerate what kinds of conditions can be asserted beyond what is hinted in the enum, nor does it explicitly differentiate from siblings like observe or watch_until.
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?
No guidance is given on when to use verify versus alternatives. There is no mention of when an assertion is preferred over observe or watch_until, nor any conditions or prerequisites (e.g., requiring a page to be open). The agent is left to infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.