Skip to main content
Glama

batch

Run multiple bridge operations in one round trip and return a result per call. Reduce latency by combining calls; a single failure won't abort the rest.

Instructions

Run several bridge operations in ONE round trip and return a result per call.

A round trip costs a poll interval plus latency against single-digit ms of actual work, so a sequence of small calls is nearly all waiting. Each entry is a dict with an "op" key:

{"op": "world"} {"op": "reload"} {"op": "find", "ref": ...} {"op": "get", "ref": ..., "name": ...} {"op": "set", "ref": ..., "name": ..., "value": ...} {"op": "call", "ref": ..., "function": ..., "args": [...]} {"op": "props", "ref": ..., "include_super": bool, "read_soft": bool, "pattern": str} {"op": "funcs", "ref": ...} {"op": "snapshot", "ref": ..., "label": str, "include_super": bool, "pattern": str} {"op": "diff", "label": str, "ref": ... (optional), "update": bool} {"op": "snapshots"} {"op": "forget", "label": str} {"op": "objects", "class_name": ..., "limit": int} {"op": "types", "pattern": ..., "limit": int} {"op": "subclasses", "ref": , "limit": int, "pattern": str} {"op": "target", "distance": num, "channel": int, "ref": ... (optional)} {"op": "watch", "ref": ..., "names": [str], "label": str, "interval_ms": int, "every": bool} {"op": "hook", "function": , "label": str, "max_args": int} {"op": "events", "since": int, "label": str, "limit": int, "clear": bool} {"op": "streams"} {"op": "unwatch", "label": str} {"op": "console", "command": ...} {"op": "dump", "kind": ...}

Each result is {op, ok, result} or {op, ok: false, error}. One failing call does not abandon the rest, so a batch is safe to use for exploration.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
callsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.4/5.0
Behavior4/5

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

Since there are no annotations, the description carries the disclosure burden. It documents per-call result shape ({op, ok, result} or error), states that one failing call does not abandon the rest, and notes round-trip cost. It also labels the batch as safe for exploration. It doesn't outline side effects of specific mutating ops, but the failure semantics are sufficient for a wrapper 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?

The structure is front-loaded with purpose and rationale, followed by an efficient code-block list of op shapes. The length is justified by the 23 op variants; every line communicates a distinct contract, and the closing result format is compact.

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?

With no annotations and no output schema, the description covers the two things an agent must know to invoke the batch correctly: how to encode each call and what to expect back. The omission of detailed field semantics (ref, update, kind) is a minor gap and keeps it just shy of fully self-contained.

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?

The schema provides only 'calls: array of objects' with 0% description coverage, so the description must compensate. It does substantially: every supported op key and its parameter skeleton is enumerated. It leaves 'ref' and several op-specific fields (include_super, read_soft, update, kind) semantically undefined, which prevents a 5.

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 first sentence states a specific verb ('Run'), resource ('bridge operations'), and a distinguishing constraint ('in ONE round trip'), and 'return a result per call' clarifies what the batch produces. This clearly separates it from the individual sibling tools such as get_property or call_function.

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?

The description explains the cost model — a round trip costs a poll interval plus latency versus single-digit ms of work — and therefore identifies when batching small calls is valuable. It doesn't explicitly say 'use instead of N individual calls' or name the alternative, but the context is clear.

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