Skip to main content
Glama
ly8427

review-board

by ly8427
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

List Comments Since

list_comments_since

Poll for new review comments since a given time, returning a needs_attention summary of new comments, mentions, and pending verdicts. Advances your delivery cursor to ensure no backlog is missed.

Instructions

Poll for new comments — the ONE call that advances your last_read cursor.

Passing author (always pass your own tool name when polling):

  • registers/heartbeats you (D1 liveness), and

  • computes the window as the UNION of since and your undelivered backlog (server-side last_read cursor): nothing already-undelivered is ever missed even if since is shorter (dsh-2). The cursor advances to this call's snapshot moment only here — get_thread/the probe/anything else never advances it (C3: cursor = "delivered to an LLM" watermark).

Returns a one-line needs_attention: JSON header {new_comments, mentions_me[{thread_id,comment_id}], awaiting_my_verdict, open_threads} — idle polls can act on the header alone without reading threads (cost model §4). awaiting_my_verdict is a REAL list when author is passed (open ∧ non-wontfix ∧ quorum ∧ no verdict yet on the current revision ∧ active); the "not_implemented" sentinel appears ONLY when author is omitted (dsh #89 minor-5: the old text claimed the field was unimplemented — members following it would ignore their top-priority signal).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sinceNoabsolute timestamp or relative '30m'/'2h'/'1d'/'now' (first-round fallback when no cursor exists yet).1h
authorNoyour tool name — poll WITH it, always.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and succeeds: it discloses the liveness heartbeat, cursor advancement side effect, union-window computation, the sentinel behavior when author is omitted, and the meaning of awaiting_my_verdict. This is far beyond what annotations or schema alone would provide, and nothing contradicts the structured data.

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?

The description is dense but front-loaded with the most important behavior. Every paragraph adds necessary semantic detail, though internal document references like 'dsh-2', 'C3', and 'dsh #89 minor-5' add background complexity that may not be resolvable by the agent. Still, it is structured and free of filler.

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

Completeness5/5

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

For a polling tool with subtle cursor semantics, the description covers the needed context: when to pass author, how the cursor advances, what the needs_attention header contains, and the sentinel edge case. An output schema exists, and the description also gives return-value guidance, so nothing critical is missing.

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. The description adds real meaning beyond the schema: author controls liveness registration and backlog-union windowing, and since is the first-round fallback when no cursor exists. This improves an agent's ability to set both parameters correctly.

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?

The description states a specific action and resource — 'Poll for new comments' — and immediately distinguishes this tool from siblings by calling it 'the ONE call that advances your last_read cursor.' An agent can tell it apart from get_thread and the probe without inspecting schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use the tool ('Poll for new comments'), how to use it correctly ('always pass your own tool name'), and what other tools cannot do ('get_thread/the probe/anything else never advances it'). This gives the agent clear selection and invocation guidance.

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