Skip to main content
Glama

Read a browser session

writ_browser_context
Read-onlyIdempotent

Re-reads an open session: section=page (url, fields, buttons, cleaned DOM), lists (the page's repeating rows with a live-tested define_function payload for writ_browser_compose), map (the evidence of the build the session is bound to).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "session_id": "<session_id>"
    },
    "name": "writ_browser_context"
  }
}

Input Schema

NameRequiredDescriptionDefault
offsetNo
sectionNopage (default) | lists | map | explorer | concierge_api.
max_charsNo
session_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / max_chars
      Added value: +{
      +  "type": "integer"
      +}
    • addedInput schema / properties / offset
      Added value: +{
      +  "minimum": 0,
      +  "type": "integer"
      +}
  2. Changed3 schema fields changed
    • removedInput schema / properties / max_chars
      Removed value: -{
      -  "description": "Characters per page (1000–10000, default 8000).",
      -  "type": "integer"
      -}
    • removedInput schema / properties / offset
      Removed value: -{
      -  "description": "Paging offset for the policy sections.",
      -  "minimum": 0,
      -  "type": "integer"
      -}
    • changedInput schema / properties / section / description
      Previous value: -"page (default) | lists | map | explorer | concierge_api"New value: +"page (default) | lists | map | explorer | concierge_api."
  3. First observed

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value by saying the read is fresh ("Re-reads") and that the lists payload is "live-tested" for downstream compose, but it says nothing about pagination/truncation behavior despite offset and max_chars parameters existing.

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

Conciseness4/5

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

One dense sentence with the action front-loaded and each section clarified inline — no filler. The nested parentheses make it harder to scan than a short bulleted list, but nothing is redundant.

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

Completeness2/5

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

For a four-parameter tool with 25% schema coverage and no output schema, the description should define offset and max_chars and cover all enum values; it does neither, and the uneven coverage (three of five sections) may mislead an agent into thinking those are the only options.

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

Parameters2/5

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

Schema coverage is only 25%, so the description must carry the param burden; it explains three of the five enum values (page, lists, map) but omits explorer and concierge_api entirely. The two limiting parameters, offset and max_chars, are given no meaning anywhere, leaving an agent to guess how to page through large DOM output.

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

Purpose4/5

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

"Re-reads an open session" gives a specific verb plus resource and immediately enumerates what each section surfaces (page url/fields/buttons/DOM, repeating rows, build map). That is enough to distinguish it from write-oriented siblings like writ_browser_compose and writ_browser_act, though no sibling is explicitly named as an alternative.

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

Usage Guidelines3/5

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

The word "Re-reads" implies the precondition that a session is already open, and the per-section breakdown helps pick a section value. But there is no explicit statement of when to call this versus writ_browser_sessions, writ_browser_live_view or writ_browser_network, and no guidance on repeated polling versus capturing state once.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.