tab_extractExtract text, links, or table data from a page using a CSS selector, with truncation warnings when results are limited.
Read bounded text, links or table data, optionally within a CSS selector. Returns truncation information when the result is limited.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| selector | No | ||
| max_items | No | ||
| session_id | Yes | Session ID returned by tab_open. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as read-only and non-destructive, and the description's 'Read' aligns with that. It adds useful behavioral context beyond annotations by disclosing that results may be bounded and that truncation information is returned when the result is limited.
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 states the core action, the data types, the optional selector, and a key return behavior. Every phrase earns its place, though 'bounded' is slightly ambiguous.
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 4-parameter tool with no output schema, the description covers the main capability and truncation behavior but omits important operational details such as how max_items applies to different kinds, what table extraction returns, and whether a default selector covers the whole page. It is adequate but has clear gaps.
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 low (25%), but the description adds meaning by naming the kind enum values ('text, links or table data') and mentioning the optional CSS selector. It does not clearly explain the semantics of max_items beyond the vague word 'bounded', nor does it describe the output shape for each kind.
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 uses a specific verb ('Read') and names concrete resources: bounded text, links, or table data, optionally scoped by a CSS selector. It clearly conveys what the tool does, though it does not explicitly differentiate itself from the similar sibling tab_extract_structured.
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 description implies usage: call this when you need to read text, links, or tables from a page, possibly within a selector. However, it gives no explicit when-to-use vs alternatives guidance, nor does it mention cases where a sibling like tab_extract_structured or tab_find would be more appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.