Skip to main content
Glama

obit_graveyard

Lists buried files and pending manifests in ID order with paging, filters results to an absolute directory, and flags when the set changes so you can restart for a full view.

Instructions

Lists burials and pending manifests together in ascending ID order; reconciles verified interrupted restores and reports their actual paths. Optional here filters original paths by an absolute directory, including descendants. Pass nextAfter as after and version to continue with the same here. changed warns when the full set changes; restart for a complete view. total counts this read. Permanent purging is a user decision.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "obit_graveyard"
  }
}

Input Schema

NameRequiredDescriptionDefault
hereNoOptional absolute Windows directory; include only original paths in this directory and its descendants
afterNoPrevious nextAfter (decimal ID string); omitted starts at the beginning
limitNoResults per page; 0 uses 200; maximum 200
versionNoPrevious page version; a different current set returns changed and a warning to restart

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

The description adds meaningful behavior beyond the annotations: ascending ID order, path filtering, pagination continuation, changed warnings, and the fact that permanent purging is a user decision. But with readOnlyHint=false and idempotentHint=false, it should more clearly explain what reconciliation mutates, whether those effects are reversible, and why the operation is not read-only.

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 purpose is front-loaded and most sentences carry operational information without excessive length. A few phrases are terse to the point of being cryptic, especially 'total counts this read,' but overall the structure is efficient and dense rather than padded.

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

Completeness3/5

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

For a four-parameter tool with no output schema and sparse annotations, the description covers purpose, filtering, pagination, and change warnings reasonably well. It still leaves gaps around return structure and the side effects of 'reconciles verified interrupted restores,' which matters because the tool is explicitly not read-only.

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, but the description adds useful relational semantics: here scopes original paths by directory and descendants, after corresponds to a previous nextAfter, and version must be reused with the same here to continue. It also explains the changed warning tied to version, which helps an agent understand how the parameters interact.

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 states a specific verb and bundled resource scope: lists burials and pending manifests, reconciles verified interrupted restores, and reports actual paths. It is clear enough to distinguish the operation generally, but it does not explicitly differentiate this from sibling tools such as obit_list or obit_resurrect, and the domain jargon makes the exact boundary less crisp.

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 description gives operational guidance for filtering with here and continuing pagination via after and version, including what to do if changed is returned. However, it does not say when to choose this tool over alternatives like obit_list, obit_resurrect, or obit_bury, so tool-selection guidance is only implied.

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