Repository Manager

Validate

rm_projects_validate

Bulk install, build, and validate Python projects, submitting validation as a background job and returning a job ID to poll for progress and results.

Instructions

Validate (rm_projects). Bulk install, build, and validate Python projects.

The 'validate' action submits validation as a background job and returns a job_id immediately. Use 'validate_status' with that job_id to poll progress and retrieve results once complete.

Input Schema

Name	Required	Description	Default
`extra`	No	Install group (e.g. 'all') for 'install'.	all
`job_id`	No	Job ID to check status for 'validate_status' action.
`summary`	No	For 'validate'/'validate_status': return a COMPACT roll-up (counts + failed set + running names) instead of the full per-job dump. Keeps responses inline-returnable at thousands of repos. Set False for the full per-job detail.
`threads`	No	Parallel workers.
`auto_bump`	No	Automatically run phased_bumpversion if validation passes. Begins at the lowest phase that has repository changes (and cascades to every later phase), skipping unchanged upstream phases.
`auto_push`	No	Automatically run phased_push if validation passes. Begins at the lowest phase with unpushed work, skipping the inter-phase waits of unchanged upstream phases.
`bump_part`	No	The part of the version to bump (e.g. minor, patch, major) if auto_bump is used.	minor
`output_dir`	No	Directory to write the validation-reports for 'validate'.
`commit_code`	No	For 'validate': after validation passes and BEFORE the version bump, concurrently stage (git add -A), run pre-commit, and commit feature code across ALL targeted repos. Ensures untracked/new files are committed (not left for the push safety net). The bump then waits on this step. Use with commit_message.
`failed_only`	No	For 'validate': target ONLY repositories whose most-recent validation failed (the remediation loop). Ignored if 'repositories' is given. Forces re-validation of that set.
`repositories`	No	Comma-separated list of specific repositories to target.
`commit_message`	No	Commit message for the commit_code step. Required when commit_code=True.
`generate_report`	No	Generate validation report directory for 'validate'. Default True.
`prune_worktrees`	No	For 'validate' with auto_bump/auto_push: after the release, prune session worktrees already merged into main (and dangling admin pointers). DESTRUCTIVE. Default False — the release still runs the audit and REPORTS the safe_to_prune/do_not_disturb classification under 'worktree_hygiene_job_id' WITHOUT deleting anything. Never touches active/in-flight or orphaned worktrees.
`force_revalidate`	No	If true, bypass validation cache and force re-validation of all projects.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.5.1Oct 19, 2026

TDQS

B3.4/5.0

Behavior3/5

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

The description adds genuine behavioral context beyond the annotations: 'validate' runs as a background job and returns a job_id immediately, explaining the async contract. The annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) only cover the mutation/safety profile; the description does not surface the side-effecting chains (auto_bump, auto_push, commit_code) or the DESTRUCTIVE prune behavior, though the schema does document those.

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?

Two compact sentences with the purpose front-loaded and then the async contract, no filler. Minor waste in the leading 'Validate (rm_projects).' which merely restates the name and title, and the description is arguably too terse for a 15-parameter tool, but nothing is bloated.

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?

An output schema exists, so return values need not be explained, and the async/job_id model is captured. Still, for a tool with 15 parameters, no action parameter in the schema despite the description referencing 'validate'/'validate_status' actions, and cascading write behavior, the description leaves an agent underinformed about scope and side effects.

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 all 15 parameters are already documented in the schema, which establishes a baseline of 3. The description adds no parameter-level meaning beyond the async job_id/validate_status relationship, so it neither compensates nor detracts.

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 scope: 'Bulk install, build, and validate Python projects,' which lets an agent separate it from single-project siblings like repository_manager_validate_single_project. However, it does not distinguish itself from the many adjacent bulk tools (rm_projects_build, rm_projects_install, repository_manager_validate_and_release) beyond the one-word 'validate' in the name.

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?

It explicitly instructs the agent to call 'validate_status' with the returned job_id to poll and retrieve results, which is real workflow guidance. But there is no when-to-use/when-not-to-use guidance against the numerous sibling validate/build/install tools, and none of the parameter-driven modes (failed_only remediation, auto_bump/auto_push chains) are routed from the description.

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

Deploy Server