Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Wait for review

review_wait
Read-onlyIdempotent

Polls a local Mergestorm review job by job_id from review_submit, returning its job envelope or in_progress so you can call again until completion.

Instructions

Read one local Mergestorm review job by the job_id that review_submit returned, as a job envelope. timeout_s: 0 reads it once without polling; otherwise it polls for one 45s slice by default (max 300s). On timeout, returns in_progress; call again with the same job_id until done. Do not pass 300; hosts drop long MCP calls. On rate_limited, wait retry_after_seconds before trying again.

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": {
      "job_id": "<job_id>"
    },
    "name": "review_wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYes
timeout_sNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations (which already cover read-only, idempotent, non-destructive), the description discloses the polling mechanics: 45s default slice, 300s max, in_progress on timeout, and the warning that hosts drop long MCP calls. It also surfaces the rate-limit contract with retry_after_seconds, which no structured field conveys.

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 read action, then the timeout semantics, then failure handling; each sentence carries operative information. Density is high, and terms like "job envelope" are used without defining what the envelope contains, which costs a little clarity.

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?

Covers the polling lifecycle and the three terminal/lateral outcomes an agent must handle (done, in_progress, rate_limited), which is what a read-only wait tool needs. What the returned job envelope actually contains is left implicit, though the absence of an output schema makes that a smaller gap.

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

Parameters5/5

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

Schema coverage is 0%, yet both parameters are fully explained: job_id must be the value review_submit returned, and timeout_s carries meaning (0 = single read without polling, default one 45s slice, 300s ceiling, and an explicit "do not pass 300" caveat). The schema alone would leave an agent guessing at all of this.

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 ("Read one local Mergestorm review job") and pins the input's provenance to review_submit, which separates it from the PR-flavored siblings such as review_wait_pr. It never explicitly says which sibling to prefer when the agent has a PR rather than a local job, so it stops short of full differentiation.

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 concrete when/how guidance: timeout_s=0 for a single read, otherwise a one-slice poll, and re-call with the same job_id on in_progress until done. It also covers the rate_limited path with retry_after_seconds. It does not address when to choose this over sibling wait tools like issue_review_wait or stack_wait.

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