Skip to main content
Glama
Sign In
hw-native-sys

hw-native-sys

by georgebisbas
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

pr_watch

Capture a read-only, one-shot PR snapshot of CI rollup, review decision, unresolved threads, reviews, comments, and new-only deltas, letting the caller control watch cadence without posting.

Instructions

Read-only one-shot PR snapshot: CI rollup, review decision, unresolved threads, reviews, comments, and new-only deltas. Never posts; the caller owns the watch cadence.

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": {
      "repo": "<repo>",
      "number": "<number>"
    },
    "name": "pr_watch"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoYesSingle allowlisted repo, e.g. "pypto". "all" is rejected.
sinceNoCursor from a previous call's cursor.next_since; empty on first call.
numberYesPull request number, e.g. 3248
seen_idsNoIDs already reported (cursor.seen_ids from the previous call).
include_resolvedNoInclude resolved review threads in the snapshot.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does real work: it declares read-only semantics ('Never posts'), states there is no internal polling loop ('one-shot', 'caller owns the watch cadence'), and discloses the delta behavior ('new-only deltas'). It does not mention authorization requirements, rate limits, or what happens when the PR is closed or the repo is not allowlisted, which keeps it out of 5 territory.

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?

Two short sentences, zero filler, with the core identity ('Read-only one-shot PR snapshot') front-loaded before the payload list. The second sentence covers the two behavioral constraints an agent most needs. Nothing is redundant with the schema.

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?

An output schema exists, so return-value detail is not required, and the description covers the operation's nature, its read-only guarantee, and its delta model. Remaining gaps are edge-case behavior: closed PRs, invalid cursors, and the allowlist rejection already noted in the repo parameter. Adequate for a five-parameter read tool.

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 description coverage is 100%, so the baseline is 3 and the schema already explains repo, number, since, seen_ids, and include_resolved individually. The description adds meaning above that baseline by framing the call as a 'new-only delta' snapshot, which tells the agent why since/seen_ids exist and that omitting them yields the full first-call snapshot.

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-only one-shot PR snapshot') and enumerates exactly what the snapshot contains: CI rollup, review decision, unresolved threads, reviews, comments, and new-only deltas. That is far more than a restatement of the name. It stops short of a 5 because it never distinguishes itself from the PR-adjacent sibling gate_pr_script, so an agent must infer the boundary.

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?

'One-shot' plus 'the caller owns the watch cadence' implies a poll-by-repeated-call pattern rather than an internal watcher, which is useful implicit guidance. However, there is no explicit statement of when to use this versus gate_pr_script or other PR/task tools, and no prerequisites (e.g., PR must be open, repo must be allowlisted) beyond what the schema already says.

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