Skip to main content
Glama
Repository Manager

Repository Manager

Fleet Evidence Check

rm_workspace_fleet_evidence_check

Performs fleet evidence check on workspace projects by validating configuration and immutable reference JSON for consistency.

Instructions

Fleet evidence check (rm_workspace). Core workspace organization and configuration.

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": "rm_workspace_fleet_evidence_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
installNoFor 'setup': after clone/pull, materialize each project's .uv-workspace-siblings/scion-sdk symlink and run `uv sync`, dependency-ordered (scion-sdk first, since every fleet member depends on it and it is not yet published to PyPI at the required floor). Best-effort per project; a partial failure is reported (status='error' with per-project detail in 'data'), never masked as a uniform success. See CONCEPT:RM-BOOTSTRAP.
yml_pathNoPath to workspace.yml (for 'setup', 'template', 'save').
config_dictNoDictionary representation of WorkspaceConfig (for 'save').
use_defaultNoUse the pre-filled package template for 'template'.
fleet_evidence_jsonNoBounded immutable reference JSON for fleet_evidence_check.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv3.5.7
    • removedInput schema / properties / auto_start
      Removed value: -{
      -  "default": true,
      -  "description": "For 'maintain': begin at the lowest phase with repository changes instead of always 'phase', cascading to every later phase and skipping unchanged upstream phases. Default True; set False to start at 'phase'. Ignored when 'projects' or 'force' is set.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / dry_run
      Removed value: -{
      -  "default": false,
      -  "description": "Perform a dry run for 'maintain'.",
      -  "type": "boolean"
      -}
    • removedInput schema / properties / force
      Removed value: -{
      -  "default": false,
      -  "description": "For 'maintain': bump even when no code changes are detected, and override an orphan local 'next-version' tag (delete it and re-bump) — only if that tag is NOT on the remote.",
      -  "type": "boolean"
      -}
    • changedInput schema / properties / install / description
      Previous value: -"For 'setup': after clone/pull, materialize each project's .uv-workspace-siblings/agent-connector-sdk symlink and run `uv sync`, dependency-ordered (agent-connector-sdk first, since every fleet member depends on it and it is not yet published to PyPI at the required floor). Best-effort per project; a partial failure is reported (status='error' with per-project detail in 'data'), never masked as a uniform success. See CONCEPT:RM-BOOTSTRAP."New value: +"For 'setup': after clone/pull, materialize each project's .uv-workspace-siblings/scion-sdk symlink and run `uv sync`, dependency-ordered (scion-sdk first, since every fleet member depends on it and it is not yet published to PyPI at the required floor). Best-effort per project; a partial failure is reported (status='error' with per-project detail in 'data'), never masked as a uniform success. See CONCEPT:RM-BOOTSTRAP."
    • removedInput schema / properties / job_id
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "Job ID to check status for 'maintain_status' action."
      -}
    • removedInput schema / properties / part
      Removed value: -{
      -  "default": "patch",
      -  "description": "Version part to bump for 'maintain' (major, minor, patch).",
      -  "type": "string"
      -}
    • removedInput schema / properties / phase
      Removed value: -{
      -  "default": 1,
      -  "description": "Starting phase number for 'maintain'.",
      -  "type": "integer"
      -}
    • removedInput schema / properties / projects
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "For 'maintain': comma-separated repo names to bump ONLY those (e.g. re-bump repos a prior run skipped) instead of the whole topological set. Restricts the bulk phase to these names."
      -}
    • removedInput schema / properties / summary
      Removed value: -{
      -  "default": true,
      -  "description": "For 'maintain_status': return a COMPACT roll-up (per-phase counts + failed set + active names + remaining count) instead of the full per-repo phase dump. Keeps the response inline at 200+ repos. Set False for the full per-repo detail.",
      -  "type": "boolean"
      -}
  2. First observedv3.5.1

TDQS

C2/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=false, so the agent knows this mutates state non-idempotently but predictably. The description adds nothing beyond that — no mention of side effects, permission needs, or the 'bounded immutable reference JSON' processing implied by the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but brevity here is under-specification rather than concision: the second sentence is a filler clause that carries no information and displaces the definition the agent actually needs. Wasted space in a two-sentence description is a structural flaw.

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?

The tool takes five parameters, mutates state, and is one of many similarly named siblings; the description supplies none of the orientation needed to call it correctly. Although an output schema exists (lowering the need to explain return values), the description still fails to convey the operation's basic premise.

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?

Schema description coverage is 100%, so each of the five parameters (install, yml_path, config_dict, use_default, fleet_evidence_json) is already documented in the schema. The description contributes no additional parameter meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first sentence merely restates the tool name ('Fleet evidence check') and the second, 'Core workspace organization and configuration,' is generic boilerplate that could describe any of the dozens of rm_workspace_* siblings. It never states what the check actually validates or produces, so an agent cannot distinguish it from rm_gates_audit_fail_fast, rm_workspace_save, or rm_projects_validate.

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

Usage Guidelines1/5

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

There is no guidance whatsoever on when to use this tool, when not to, or which sibling it substitutes for. Given the crowded sibling set (gates, workspace setup/template/save, projects validate), this omission leaves selection entirely to guesswork.

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