Skip to main content
Glama
Sign In
doc-review

doc-review

by MichaelEight
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

review_wait

Blocks until the user sends new document comments, then returns each with file, line, quoted text, context, thread history, referenced files/tags, and any round instruction.

Instructions

Block until the user presses "Send to AI", then return every new comment with its file, line, quoted text, context and thread history, plus referenced @files and #tags, and the user's standing instruction for the round if they set one (it overrides the default of editing the files; follow it). Ends the previous round. Returns {status:"timeout"} after timeout_seconds; then call it again to keep listening. This blocks for minutes, so make sure the UI url is already in a chat message before you call it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "review_wait"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootNoAbsolute path of the workspace folder. Optional when only one workspace is open.
timeout_secondsNoDefault 540.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses that the call blocks for minutes, that it ends the previous round (a real side effect), the timeout sentinel value, the retry pattern, and that a user-supplied instruction overrides the default editing behaviour. This is exactly the behavioural context an agent needs before a long-blocking call.

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-loads the blocking behaviour and the trigger condition, and the enumerated return fields are justified because there is no output schema to carry them. The first sentence is dense with nested parentheses and clauses, which costs some readability.

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?

Given no annotations and no output schema, the description supplies the return shape, the timeout contract, and the side effect on the previous round. Minor gaps remain: no guidance on failure/auth conditions and no statement about how 'new' is tracked across calls.

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 baseline is 3, but the description adds meaning beyond the schema by explaining the consequence of timeout_seconds (a {status:"timeout"} return and the need to re-call). The `root` parameter is not addressed, but its schema description is adequate.

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 mechanism ("Block until the user presses 'Send to AI'" and returns new comments) rather than a generic 'get comments'. It distinguishes itself from lookup-style siblings like review_threads by scoping to *new* comments for a round and ending the previous round.

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 clear situational guidance: call it to listen, call it again after a timeout, and ensure the UI url is already posted before blocking. It doesn't explicitly contrast with review_threads (which presumably fetches existing comments non-blockingly), so the 'when not to use' side is only implied.

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