cdp_snapshotCapture an accessibility snapshot of a browser tab and return numeric refs to pass to cdp_click for element targeting.
Accessibility snapshot with numeric refs; feed a ref to cdp_click.
| Name | Required | Description | Default |
|---|---|---|---|
| tab | No | Tab index from cdp_tabs to act on. | |
| url | No | Pick the tab whose URL contains this substring. | |
| port | No | CDP debug port (default 9222). |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive, so the safety profile is fully covered. The description adds that the tool returns numeric refs consumable by cdp_click, which is a genuine behavioral detail beyond the annotations, but it says nothing about snapshot scope, refresh behavior, or whether refs persist across navigations.
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?
A single front-loaded clause delivers the core purpose and the downstream action with no filler. The semicolon-joined second clause is efficient, though the terseness leaves a few questions unaddressed.
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 read-only snapshot tool whose annotations cover safety and whose parameters are fully documented, the description is adequate but thin. It does not clarify snapshot scope or output shape, and with no output schema present the description carries more of that burden than it does.
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% and all three parameters (tab, url, port) are documented in the schema, so the description need not repeat them. It adds no syntax or precedence detail for the tab/url selection, making the baseline 3 correct.
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 states a specific resource ('accessibility snapshot') and a distinctive output trait ('numeric refs'), which separates it from the pixel-based cdp_screenshot and the desktop_* family. It does not explicitly name a non-goal or contrast itself with the visually similar desktop_snapshot sibling, so it falls short of a 5.
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 'feed a ref to cdp_click' implies the intended workflow (snapshot first, then act on a ref), which is useful implied guidance. However, it never states when to choose this over cdp_screenshot or desktop_snapshot, and there are no explicit exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.