Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Watch live prospect research

watch_research
Read-onlyIdempotent

Tracks live progress of one research job: prospect/email counts, stage, findings, blockers, and final-response readiness. Use a cursor to long-poll for updates; read-only.

Instructions

Live progress of one existing research job. The first call returns at once with a cursor; later calls with that cursor wait up to about 25 seconds for a change. Returns saved prospect and email counts, stage, up to three findings with evidence, blockers, follow-up suggestions, continue_watching, final_response_ready (true only when the job is finished) and next_tool_arguments. Routine queued and running churn is coalesced. Worker steps and preview rows are not found prospects. Reads only; creates no work.

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": {
      "goal_id": "<goal_id>"
    },
    "name": "watch_research"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNo
goal_idYes
timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description adds real behavior beyond that: cursor-based long polling with a ~25s block, coalescing of routine queued/running churn, and the caveat that worker steps and preview rows are not counted as found prospects. It omits error behavior for an invalid or expired goal_id, and 'Reads only; creates no work' largely repeats readOnlyHint.

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?

Front-loaded with the core action and polling contract, then the return payload, then caveats. Dense but every clause carries usable information except the closing 'Reads only; creates no work', which duplicates the readOnlyHint annotation.

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?

There is no output schema, so the description must describe returns, and it enumerates counts, stage, findings with evidence, blockers, suggestions, continue_watching, final_response_ready, and next_tool_arguments. Remaining gaps are what happens on an invalid/expired goal_id and how next_tool_arguments is meant to be used, which matter for a polling tool.

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

Parameters4/5

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

With 0% schema description coverage the description must carry the load, and it does for cursor (format of the polling token and where it comes from) and timeout_seconds (the ~25 second wait, matching the schema default and maximum). goal_id is only indirectly explained as identifying 'one existing research job', so the mapping of the parameter to a research job id is left somewhat implicit.

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 action and resource: live progress watching of one existing research job, with a clear terminal condition (final_response_ready true only when finished). It implicitly separates itself from answer-fetching siblings like get_research_answer by emphasizing live progress rather than a final answer, but it never names an alternative explicitly.

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?

The polling protocol is spelled out: first call returns immediately with a cursor, subsequent calls with that cursor long-poll for up to ~25 seconds. It signals continuation via continue_watching and routing via next_tool_arguments. It never states when not to use it (e.g., once finished, use a different tool), so it falls short of explicit exclusions.

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