Extract structured page text by mapping CSS selectors to content in an existing Firefox or Chromium session. Target a specific tab or browser profile when needed.
Extract selector->text map
| Name | Required | Description | Default |
|---|---|---|---|
| map | Yes | ||
| tab | No | ||
| profile | No | Browser ID from sleeper_sessions; optional with one connected browser. |
Changes observed during successful MCP inspections.
v2.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden of behavioral disclosure, and it says nothing about side effects, required session/auth state, or failure modes. A terse 'extract' fragment leaves the agent blind to whether this mutates state, requires an active tab, or blocks.
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?
It is a single short fragment; brevity here reflects under-specification rather than efficient front-loading. There is no wasted sentence, but there is also not enough substance to constitute a usable definition.
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 tool with a required nested-object parameter, no annotations, no output schema, and low schema coverage, the description leaves everything an agent needs to invoke it correctly unstated. It is not complete at any useful level.
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?
Three parameters with only 33% schema coverage: only 'profile' is documented, while the required nested object 'map' and 'tab' are bare. The phrase 'selector->text map' hints at the 'map' object's purpose but is ambiguous about whether it is an input specification or the return shape, 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?
The fragment 'Extract selector->text map' gestures at a verb (extract) and a result (selector-to-text mapping) but is grammatically incomplete and doesn't state what is being extracted, from where, or how it differs from siblings like sleeper_get, sleeper_read, or sleeper_find_text. An agent cannot reliably distinguish this from related extraction/read tools on the text alone.
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?
There is no when-to-use guidance, no mention of prerequisites (e.g., needing a page loaded or a browser session), and no reference to any alternative tool among the ~50 siblings. The description provides no routing signal at all.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.