Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Wait for recording

wait_for_recording
Read-onlyIdempotent

Waits for a browser recording made after a given start time. Returns the recording once available or a waiting status if the timeout ends.

Instructions

Waits for a recording the user is making in the browser. Returns status found with the recording as soon as one made after since exists, or status waiting when the wait window ends. A found recording may still be editing. Reads only.

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": {
      "since": "<since>"
    },
    "name": "wait_for_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceYesThe started_at value from start_browser_recording.
account_idNo
timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover read-only and idempotent, but the description adds real behavior: the two possible statuses (found vs waiting), that found is returned as soon as a qualifying recording exists, and the nontrivial caveat that a found recording may still be editing. It does not describe what happens on timeout expiry beyond 'wait window ends', but the key semantics are disclosed.

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?

Four compact sentences, front-loaded with the purpose and followed by return semantics and the editing caveat; no wasted words. Only the trailing 'Reads only.' is redundant with readOnlyHint.

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?

No output schema exists, and the description does explain the two return statuses and the meaning of a 'found' result, so the return contract is largely covered. The gap is the wait-window/timeout behavior, which is central to a blocking wait operation and is left unexplained.

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?

With only 33% schema description coverage, the description partially compensates by explaining that 'since' is the threshold that determines 'made after', which clarifies its meaning. However, timeout_seconds and its 50-second cap are undocumented anywhere, and the description gives no hint about the wait window length.

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?

States a specific verb and object ('Waits for a recording the user is making in the browser'), which is clearly distinct from a generic task wait. It does not explicitly name or contrast with the closest sibling (start_browser_recording / wait_for_task), so it falls short of full sibling differentiation.

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?

Usage context is implied through the phrase 'one made after since exists' and the schema note that 'since' comes from start_browser_recording, but the description itself never says when to call this versus polling get_recording or waiting on a task. No exclusions or prerequisites are stated.

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