Skip to main content
Glama
Sign In
umbra

umbra

by lxchx
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Route Captures

route_captures

Retrieve captured request and response data for a specific routing rule in a browser tab, and optionally drain the buffer after reading.

Instructions

Return per-rule capture buffer (filled when rule has capture=N). Each entry: {ts, url, method, status, request_headers, body, body_encoding?, error?}. Use clear=True to drain after read.

Ex: route_captures('t0','r2') → {"_untrusted":true,"id":"r2","captures":[...]}

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": {
      "tab_id": "<tab_id>",
      "rule_id": "<rule_id>"
    },
    "name": "route_captures"
  }
}

Input Schema

NameRequiredDescriptionDefault
clearNo
tab_idYes
max_strNo
rule_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description has to carry the full disclosure burden. It does communicate one genuinely behavioral fact -- that `clear=True` drains the buffer, i.e. the read can be destructive -- but the entry-field listing largely restates the output schema (has_output_schema=true), and it says nothing about buffer size caps, whether drained captures are recoverable, or what happens when a rule has no `capture` set.

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?

Three short sentences plus a call example, with the buffer/rule relationship front-loaded and the drain caveat placed before the agent commits to a call. Zero filler.

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

Completeness4/5

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

Output schema exists, so the entry shape did not need restating; the description nonetheless grounds the agent in the return format and the drain behavior. The one meaningful hole for a 4-param read tool is the unexplained `max_str` truncation semantics.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate for 4 params. It covers `clear` explicitly and `tab_id`/`rule_id` implicitly via the example call, but `max_str` (default 4000) -- almost certainly a truncation limit on `body`/header strings -- is never explained, leaving one of four parameters semantically opaque.

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?

Specific verb + resource: returns the per-rule capture buffer and immediately anchors it to the feature that populates it (`capture=N` on a rule), which distinguishes it from generic network-log siblings like get_network_requests. It stops short of naming any sibling explicitly, so the differentiation is inferred rather than stated.

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

Usage Guidelines4/5

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

Clear context for use: only meaningful once a rule is created with `capture=N`, and the post-read drain pattern (`clear=True`) is spelled out. No explicit 'when to use this instead of get_network_requests / har_dump' comparison is offered, so the agent must infer the alternative.

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

Deploy Server

Other Tools