Skip to main content
Glama

project_snapshot

DestructiveIdempotent

Queue a content-addressed snapshot of native project files, including edits made by ordinary file tools, to preserve reproducible state for simulation tasks.

Instructions

Queue content-addressed snapshot of native files, including edits made by the agent's ordinary file tools.

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": {
      "task_id": "<task_id>",
      "revision": "<revision>",
      "op_id": "<op_id>"
    },
    "name": "project_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
op_idYes
pathsNo
tokenNo
task_idYes
revisionYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.1/5.0
Behavior3/5

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

The description adds real context beyond the annotations: 'Queue' signals an asynchronous, deferred operation rather than an immediate write, and 'content-addressed' implies deduplication by content hash. However, the annotations declare destructiveHint=true and the description never says what is destroyed, overwritten, or superseded, nor what the token or revision gating means for safety.

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?

A single front-loaded sentence with the verb first and no filler; every clause carries information. It is arguably too terse rather than padded, which is a completeness problem, not a verbosity one.

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

Completeness2/5

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

This is a destructive, queued mutation with three required parameters and an output schema, so the description need not explain return values. It nonetheless leaves the destructive semantics and all five parameter meanings unaddressed, which is a substantial gap for a write tool of this shape.

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

Parameters2/5

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

Schema description coverage is 0% across five parameters (op_id, paths, token, task_id, revision), so the schema supplies only names and types. The description explains none of them — not what a revision refers to, what the token authorizes, or whether omitting paths snapshots everything — leaving required inputs such as task_id and revision semantically opaque.

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 ('Queue content-addressed snapshot of native files') and adds scope detail that the agent's own edits are included. It does not distinguish this from plausible siblings such as backup_create or project_export, so the agent still has to guess which snapshot mechanism to use.

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?

The phrase 'including edits made by the agent's ordinary file tools' implies the situation where this is appropriate (capturing work after in-place edits), but there is no explicit when-to-use, when-not-to-use, or named alternative among project_export, backup_create, or artifact_register. Usage is inferred rather than stated.

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