Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Check research progress

wait_for_task
Read-onlyIdempotent

Polls a research goal for changes in saved stage, contacts, or email counts and returns when progress updates or the wait window ends. Use it to monitor background work without creating new tasks.

Instructions

Checks existing background research and returns when a saved stage or count changes, or after a polling window of at most 10 seconds. Returns task.current_step, state, saved contact and email counts, blockers and progress_changed_during_wait (which compares polls within this one call). Worker steps are not contacts. historical_snapshot=true follows the exact requested goal. 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": "wait_for_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
goal_idYes
timeout_secondsNo
historical_snapshotNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already cover readOnly, idempotent, and non-destructive, so the bar is lower; the description still adds real value by naming the returned fields (task.current_step, state, contact/email counts, blockers, progress_changed_during_wait) and clarifying that worker steps are not contacts and that historical_snapshot pins to the originally requested goal. The one flaw is the claim of 'a polling window of at most 10 seconds', which conflicts with the schema's timeout_seconds maximum of 50 and misstates the achievable wait behavior.

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 behavior and the return contract, and the 'Worker steps are not contacts' and 'Reads only; creates no work' clauses each carry real disambiguating weight. It is dense but not padded; the only waste is the inaccurate 10-second framing.

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

Completeness3/5

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

With no output schema, the description does the right thing by enumerating return fields, and it clarifies the scope of progress_changed_during_wait as comparing polls within a single call. It is still missing error/terminal-state behavior (what happens if the goal is finished or invalid) and any differentiation from the other polling/fetch siblings, which matters for a 3-parameter wait tool.

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 description coverage is 0%, so the description must carry all three parameters. It gives only a cryptic gloss for historical_snapshot ('follows the exact requested goal'), leaves goal_id entirely unexplained, and actively misdescribes timeout_seconds by framing the window as 'at most 10 seconds' when the schema allows 0-50 with a default of 10.

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 resource ('Checks existing background research') and describes the return condition (saved stage or count change, or polling window expiry), which is much clearer than a bare 'wait'. It does not distinguish itself from plausible siblings such as get_task, watch_research, or get_research_answer, so an agent must infer the split from the phrase 'existing background research'.

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 phrase 'Checks existing background research' implies this is a poll-until-change tool rather than a one-shot fetch, which is useful implied guidance. There is no explicit when-to-use vs get_task/watch_research, no prerequisite that a research request must already exist, and no guidance on when not to call it (e.g., after the task is terminal).

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