Skip to main content
Glama
MCP Agent Operations

MCP Agent Operations

capture_repository_state

Read-only

Capture an opaque, process-local checkpoint of a Git worktree without modifying repository files, enabling deterministic agent operations to resume or compare state safely.

Instructions

Capture an opaque process-local checkpoint without changing the repository.

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": {
      "repository_root": "<repository_root>"
    },
    "name": "capture_repository_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
repository_rootYesAbsolute Git worktree beneath a configured workspace root.

Output Schema

NameRequiredDescriptionDefault
checkpoint_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.15.1

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered; the description adds genuinely new facts — that the result is opaque to the caller and scoped to the current process (lifetime-bound, not persisted). 'Without changing the repository' partly restates readOnlyHint, but reframes it in repository terms, which is still useful.

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?

A single sentence, front-loaded with the action, with no filler or redundancy. Both qualifiers ('opaque', 'process-local', 'without changing the repository') carry distinct information.

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 annotations covering safety, the schema covering the sole parameter, and an output schema covering the returned handle, the description only needs to explain lifetime and semantics — which it does via 'opaque' and 'process-local'. What is missing is the operational context of when this checkpoint should be taken, which is the main residual gap.

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

Parameters3/5

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

There is exactly one parameter and schema description coverage is 100%, with repository_root fully documented in the schema. The description adds nothing about that parameter (no constraints on which worktree roots are valid), so this sits at the baseline where the schema does all the work.

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?

The description gives a specific verb and object ('Capture an opaque process-local checkpoint') plus a scope qualifier ('without changing the repository'), which is clearly distinct from the claim_*/reference_*/skill_* siblings. The one weakness is that 'opaque process-local checkpoint' is jargon — an agent learns the shape of the action but not what the checkpoint is conceptually for.

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

Usage Guidelines2/5

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

There is no when-to-use guidance at all: no condition that selects capture_repository_state over the many claim_*/reference_* siblings, and no prerequisite or lifecycle note beyond 'process-local'. The agent must infer the trigger condition entirely.

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