Skip to main content
Glama

charlotte_observe

Get the current page state with adjustable detail levels (minimal, summary, full) and views (default, tree, tree-labeled). Optionally scope to a CSS selector or include computed styles.

Instructions

Get current page state without performing any action. Use detail levels to control verbosity: "minimal" for landmarks, headings, and interactive element counts by landmark (use charlotte_find to get specific elements with actionable IDs, or observe({ detail: "summary" }) to see all elements), "summary" (default) for content summaries and full element list, "full" for all text content. Use view: "tree" for a compact structural outline (cheapest orientation tool), or view: "tree-labeled" to include labels on interactive elements (still much cheaper than minimal JSON, and shows which button/link/input is which).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
detailNo"summary" (default), "full" (includes all text content), "minimal" (landmarks + interactive only)
viewNo"default" (structured JSON), "tree" (compact structural outline — element types only, cheapest), or "tree-labeled" (structural outline with interactive element labels — shows which button/link/input is which, still ~70% cheaper than minimal JSON)
selectorNoCSS selector to scope observation to a subtree
include_stylesNoInclude computed styles for visible elements (default: false)
output_fileNoWrite observation data to this file path instead of returning inline. Relative paths resolve against output_dir (see charlotte_configure). Returns only a confirmation with the file path and size.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description fully carries the behavioral transparency burden. It declares the tool is non-destructive ('without performing any action') and explains the behavior of each detail level and view, including cost implications.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: purpose first, then details for detail parameter, then view parameter. Every sentence adds value, and it is concise while being comprehensive. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema and 5 parameters, the description adequately explains the output format for each view ('structured JSON', 'compact structural outline') and mentions the output_file option. It is complete for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant meaning beyond the schema. It explains what each detail level returns (landmarks, content summaries, full text) and what each view produces (compact outline, labeled outline with cost savings). This adds context not present in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get current page state without performing any action.' It distinguishes itself from sibling tools like charlotte_find, which is used for getting specific elements.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use different detail levels and views, and mentions alternatives like charlotte_find. It explains the trade-offs, such as 'cheapest orientation tool' for tree view.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TickTockBent/charlotte'

If you have feedback or need assistance with the MCP directory API, please join our Discord server