Skip to main content
Glama

SHPBL: Repository Audit & Repair

by com.shpbl

Register a Build Intent and resolve its licence

build_intent
Read-onlyIdempotent

The gate between discovery and creation. Register one Build Intent — what you found in the host, what SHPBL already possesses, what new software becomes possible, why neither parent does it alone, and the tests that would prove it — and this returns the mechanical verdict: the invariants it passed, whether it rests on SHPBL's licensed reusable intelligence, whether this caller may execute the foundry, the terminal state to report, and where an authorised artifact may come to rest. Free to call at every level. Every COMPOSE, SPECIALIZE and CREATE must pass through this before any source is written; never assume authority and never write a refused artifact yourself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoYour SHPBL Practitioner key (shpbl_mcp_…). Optional if your client sends it as the `Authorization: Bearer …` header.
intentYesThe Build Intent record; every field it asks for is part of the evidence, and each field carries its own description in this schema. Required: `build_intent_id`, `proposed_artifact_id`, `proposed_name`, `proposed_type`, `host_repository`, `host_source_paths`, `host_behavior`, `host_problem`, `new_behavior`, `novelty_statement`, `planned_interface`. Tests are mandatory in effect: at least one entry across `planned_unit_tests`, `planned_behavior_tests` and `planned_integration_tests` (the aliases `planned_tests`, `unit_tests`, `behavior_tests` and `integration_tests` are folded into those three).
cml_licenseNoThe licence key from a purchased Complete Master Library. Perpetual rights to that release count as execution authority on their own — no subscription needed.
governor_keyNoGovernor authority. Only a Governor-resolved call may stage an artifact for SHPBL's global corpus.

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false. The description adds genuine context on top: the exact contents of the verdict (invariants passed, licensed-intelligence basis, caller authority, terminal state, authorized artifact location) and the 'free to call at every level' permission model. The warning 'never write a refused artifact yourself' reinforces the read-only semantics and is fully consistent with the annotations — no contradiction.

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 description is longer than average but every clause earns its place: the opening gate metaphor front-loads purpose, the verdict list enumerates return semantics the schema cannot express, and the closing directives carry both usage guidance and behavioral warnings. It could be tightened, but the density is information, not filler — appropriate for a tool this complex.

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?

For a complex gate tool with a ~30-field nested intent object and no output schema, the description compensates well by spelling out the verdict components, the mandatory sequencing before COMPOSE/SPECIALIZE/CREATE, and the caller-authority check. The rich 100%-covered schema handles parameter meaning, and the annotations cover the safety profile. The only gap is that return values are described conceptually rather than structurally, but the description's verdict enumeration largely fills that void.

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 the schema already documents every field including aliases and cross-field invariants. The description's parenthetical ('what you found in the host, what SHPBL already possesses, what new software becomes possible, why neither parent does it alone, and the tests that would prove it') adds meaningful framing that maps onto intent subfields like host_behavior/host_problem, cml_parent_ids, novelty_statement, and planned_tests. This earns a slight bump, but the schema remains the primary carrier of parameter meaning.

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

Purpose5/5

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

The description names a specific verb and resource — 'Register one Build Intent' — and immediately frames the tool as 'the gate between discovery and creation' with a concrete output: a mechanical verdict of invariants, licensing, authority, terminal state, and artifact placement. This clearly distinguishes it from siblings like write_to_repo (which writes source) and the repo-evaluation tools (harvest/evaluate/fix), leaving no ambiguity about its role in the pipeline.

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

Usage Guidelines4/5

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

The description gives strong contextual guidance: 'Every COMPOSE, SPECIALIZE and CREATE must pass through this before any source is written' and 'never write a refused artifact yourself' — an explicit directive about when to invoke this gate and how to behave afterward. It stops short of naming sibling alternatives (e.g., write_to_repo) by name for the when-not-to case, but the sequencing rule is unmistakable.

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

All SHPBL: Repository Audit & Repair toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation4/5

Most tools target distinct stages or resource types: evaluate/fix/harvest are clearly separate audit phases, and write_to_repo/list_repos are unambiguous. The library_* trio is mostly separable but library_document and library_index both offer access to volumes, and run_gauntlet partially overlaps the individual stage tools, so a couple of boundaries are less crisp.

Naming Consistency4/5

Names are uniformly lowercase snake_case and mostly follow a verb_noun pattern: evaluate_repo, fix_repo, harvest_repo, write_to_repo, list_repos, run_gauntlet. A few are noun_noun or resource-prefixed like library_search, library_document, subscription_status, and welcome/selfcheck_mcp are one-offs, so it is predictable but not perfectly uniform.

Tool Count5/5

At 14 tools the server sits within the ideal 3-15 range, and each tool has a plausible role in the audit/repair, library, or operational workflow. The count is on the larger side but justified by separate free and Practitioner lanes, library services, and health/status checks.

Completeness4/5

The core audit lifecycle is well covered: list/scope, evaluate, fix, harvest, write back, plus library search and run orchestration. The main gap is that build_intent explicitly gates COMPOSE/SPECIALIZE/CREATE operations, but no actual compose/specialize/create tools are exposed, and there is no explicit run_gauntlet cancellation or reset, though agents can work around both.

Resources