Repository Manager

List

rm_concepts_list

Read-onlyIdempotent

Lists concept claims from the central authority so you can review reservation states, namespace or prefix filters, and page through results.

Instructions

List (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 (agent_connector_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.

Input Schema

Name	Required	Description	Default
`limit`	No	For list: page size.
`state`	No	For list: filter by claim state.
`branch`	No	For reserve, optional.
`cursor`	No	For list: opaque page cursor.
`purpose`	No	For reserve.
`base_sha`	No	For reserve, optional.
`lane_ref`	Yes	Lane/worktree identity for fragment provenance.
`candidate`	No	For verify_candidate: a serialized Candidate contract payload.
`namespace`	No	For reserve (required) or list (optional filter).
`owner_ref`	No	For release/materialize (must match the claim owner).
`repo_path`	No	For verify_candidate/verify_generation: the Git repository to diff.
`repo_root`	Yes	Repository working tree root.
`candidates`	No	For verify_generation: serialized Candidate contract payloads.
`concept_id`	No	For reserve.
`design_ref`	No	For reserve, optional.
`generation`	No	For verify_generation: a serialized Generation contract payload.
`tenant_ref`	Yes	Authenticated tenant scope.
`workitem_ref`	No	For reserve, optional.
`run_trace_ref`	No	For reserve, optional.
`concept_prefix`	No	For list: filter by concept-id prefix.
`expected_fence`	No	For release/materialize: the claim's current fence.
`repository_ref`	No	For reserve.
`reservation_id`	No	For get/release/materialize.
`provenance_refs`	No	For reserve, optional.
`request_key_ref`	No	For reserve: idempotency key.
`source_tree_ish`	No	For reconcile: the tree-ish to scan for markers.	HEAD

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.5.1Oct 19, 2026

TDQS

C2.2/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description's only added claim is that 'every mutating action refuses with dependency_blocked' when the authority is missing — behavior for other operations, not this one, and it never says whether list itself works offline or fails. Value added is marginal and partly misdirected.

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 prose is repetitive and back-loaded with an architecture rationale ('thin, MCP/CLI-neutral consumer of an injected authority port') while the single actionable fact — that it lists concept-id claims — appears only as a parenthetical. Structure does not front-load what an agent needs.

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?

An output schema exists so return-shape explanation is unnecessary, but with a 26-parameter union schema spanning list/reserve/get/release/materialize/verify/reconcile, the description should clarify which parameters apply to a list call and what it enumerates. None of that context is present.

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 every of the 26 parameters carries its own description (including which operation each belongs to), so the schema does the heavy lifting and baseline 3 applies. The description adds nothing about the list-relevant filters (state, namespace, concept_prefix, cursor, limit), but per the coverage rule no penalty below baseline.

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 'List (rm_concepts)' merely restates the tool name, and the remaining text describes the rm_concepts family's architectural relationship to 'RMDD-16's central authority' rather than what this tool lists (concept-id claims/reservations). An agent cannot tell what the tool returns or how it differs from rm_concepts_get, rm_concepts_reserve, or rm_concepts_reconcile.

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?

No statement of when to use list versus the seven sibling rm_concepts_* operations, and no conditions or prerequisites for listing. The only contextual sentence concerns mutating actions refusing when the authority is unavailable, which is irrelevant to a read-only list and gives no routing guidance.

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

Deploy Server