Skip to main content
Glama
Repository Manager

Repository Manager

Verify Candidate

rm_concepts_verify_candidate
Read-onlyIdempotent

Verifies a candidate concept-ID claim against the central authority and blocks actions with a named dependency error when authority is unavailable, preventing local ID allocation.

Instructions

Verify candidate (rm_concepts). Concept-id claim coordination against RMDD-16's central authority.

Repository-manager never allocates a concept id itself: every action here is a thin, MCP/CLI-neutral consumer of an injected authority port. When the central authority (scion_sdk.governance. concept_reservation) is unavailable in this environment, every mutating action refuses with a named dependency_blocked/ConceptAuthorityUnavailable error instead of fabricating a local allocation -- it never mints or reuses an id on its own.

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": {
      "repo_root": "<repo_root>",
      "tenant_ref": "<tenant_ref>",
      "lane_ref": "<lane_ref>"
    },
    "name": "rm_concepts_verify_candidate"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoFor list: page size.
stateNoFor list: filter by claim state.
branchNoFor reserve, optional.
cursorNoFor list: opaque page cursor.
purposeNoFor reserve.
base_shaNoFor reserve, optional.
lane_refYesLane/worktree identity for fragment provenance.
candidateNoFor verify_candidate: a serialized Candidate contract payload.
namespaceNoFor reserve (required) or list (optional filter).
owner_refNoFor release/materialize (must match the claim owner).
repo_pathNoFor verify_candidate/verify_generation: the Git repository to diff.
repo_rootYesRepository working tree root.
candidatesNoFor verify_generation: serialized Candidate contract payloads.
concept_idNoFor reserve.
design_refNoFor reserve, optional.
generationNoFor verify_generation: a serialized Generation contract payload.
tenant_refYesAuthenticated tenant scope.
workitem_refNoFor reserve, optional.
run_trace_refNoFor reserve, optional.
concept_prefixNoFor list: filter by concept-id prefix.
expected_fenceNoFor release/materialize: the claim's current fence.
repository_refNoFor reserve.
reservation_idNoFor get/release/materialize.
provenance_refsNoFor reserve, optional.
request_key_refNoFor reserve: idempotency key.
source_tree_ishNoFor reconcile: the tree-ish to scan for markers.HEAD

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.5.1

TDQS

C2.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description does add real context: a named 'dependency_blocked'/'ConceptAuthorityUnavailable' failure when the central authority is absent, and the guarantee that no id is ever minted or reused locally. However, the emphasis on 'every mutating action' is largely irrelevant to this read-only verify tool, and the description never explains what verification returns or what a failed verification looks like.

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?

The description is not front-loaded: it opens with a name restatement, then spends most of its length on internal implementation detail (injected authority ports, the scion_sdk.governance.concept_reservation module path) that does not help an agent decide or invoke. That space would be better spent on what verify does.

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 and the schema is fully documented, so return values and parameter meaning are covered elsewhere. But for a 26-parameter polymorphic tool, the description leaves the core question — what verification of a Candidate contract entails and what makes it pass or fail — unanswered.

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%, and each property is explicitly tagged with the operation it belongs to (e.g. 'For verify_candidate: a serialized Candidate contract payload'), so the schema carries the parameter burden. The description adds nothing about the key verify-specific inputs such as candidate, repo_path, or the required repo_root/tenant_ref/lane_ref triple, which is the baseline 3 case.

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 opening sentence 'Verify candidate (rm_concepts)' merely restates the title, and the rest of the description explains the family's authority-port architecture rather than what verification actually checks or produces. 'Concept-id claim coordination against RMDD-16's central authority' is a family-level scope statement that would apply equally to rm_concepts_reserve, rm_concepts_release, and rm_concepts_reconcile, so it does not distinguish this sibling.

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 guidance on when to call verify_candidate versus verify_generation, get, or reconcile, and no mention of prerequisites such as needing a reserved claim first. The only conditional statement is an environmental failure mode, not a usage rule.

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