Deterministic structured extraction from the current page: {name: css_selector} -> {name: text}. More robust + cheaper than re-snapshotting and parsing.
| Name | Required | Description | Default |
|---|---|---|---|
| fields | Yes | {name: css_selector} | |
| browser_id | Yes | from browse_open |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. Description adds that extraction is 'deterministic' and provides cost/robustness comparison, which is valuable behavioral context beyond the annotations.
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, front-loaded with purpose. Every sentence adds value without redundancy. Extremely concise.
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?
Explains what extraction produces (text from CSS selectors) and positions relative to sibling tools. Does not cover edge cases like missing elements or multiple matches, but for a simple extraction tool, it is sufficiently complete.
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 coverage is 100% with descriptions for both parameters. The description reinforces the fields format and adds the output structure ({name: text}), adding meaning beyond 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?
Clearly states it performs deterministic structured extraction from the current page using CSS selectors. Distinguishes from sibling tools like browse_snapshot by emphasizing it's more robust and cheaper than re-snapshotting.
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?
Explicitly says it's 'more robust + cheaper than re-snapshotting and parsing', guiding when to use it as an alternative. Lacks explicit 'when not to use', but the comparative statement provides sufficient usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools serve similar purposes (e.g., web_read vs browse_read, web_discover vs browse_discover, research vs web_search + browse). Descriptions help differentiate, but the overlap is notable.
Most tools use a consistent verb_noun snake_case pattern (e.g., archive_message, browse_navigate). Minor deviations like standalone 'browse' and 'identity' are acceptable.
57 tools is very high for a single server, even with discover_tools. The broad domain coverage does not justify the count; it feels overloaded.
Covers identity, memory, browsing, human tasks, errands, messaging, and research comprehensively. Minor gaps might exist (e.g., no explicit agent-to-agent contract tools), but core workflows are well-supported.