Skip to main content
Glama

Wait for a research project

wait_for_project
Read-only

Blocks until a research project needs your input or finishes, then reports its current status; if still working, call again with the returned after_seq.

Instructions

Wait until a research project needs the user or has finished (its state is no longer queued or working), up to wait_seconds, then say where it stands as get_project does. Free. If it is still working, call it again with the after_seq it returns.

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": {
      "project_id": "<project_id>"
    },
    "name": "wait_for_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
after_seqNoThe after_seq the last call returned (start_project, message_project, act_on_project or this)
project_idYesThe project id
wait_secondsNoHow long to wait (default 55, at most 240)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.7.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds genuinely new behavioral facts: the call blocks up to wait_seconds, it costs no credits ('Free'), and it uses a cursor-based resume pattern. It does not say what happens on timeout beyond the re-call hint (e.g., whether an error is raised or a partial state returned), leaving a small gap for a blocking tool.

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, front-loaded with the wait condition and payout, followed by cost and the resume instruction. No filler and no repetition of schema text.

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 handles that by pointing at get_project for the result shape, which is adequate though it assumes the agent knows that sibling's output. For a blocking poll tool the essentials (termination condition, cost, retry loop) are all covered.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds operational meaning to after_seq by tying it to the returned value and the re-invocation loop rather than just its type. wait_seconds limits are left to the schema, which already documents the default and cap.

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

Purpose5/5

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

States a specific verb and resource ('wait until a research project...') plus the exact termination condition (state is no longer queued or working). It also distinguishes itself from the passive read by noting it reports 'as get_project does' after waiting, so an agent can tell the two apart without opening schemas.

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?

Gives the operative loop guidance: if it is still working, call it again with the returned after_seq. It implies get_project is the non-blocking alternative but never states when to prefer that instead of waiting, so the guidance is strong but not fully explicit about alternatives.

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