biz.dfch.SpecMgr

Overview Schema Source Related Servers Discussions Admin

List ADRs

list_adr

Lists Architecture Decision Records one page at a time, showing IDs, titles, statuses, and refs so you can find the right record before retrieving it by ID.

Instructions

Ids, titles, statuses, and refs of ADRs in the configured ADR base directory (SPECMGR_ADR_DIR), one page at a time, for context before addressing one by id. 'ref' is an opaque, extensionless identifier -- not a filename to read from disk -- for documents that have no assigned id; use get_adr with it instead. max_results/offset control paging (default page size 25, capped at 100); out-of-range values are clamped, not errored.

Input Schema

Name	Required	Description	Default
`offset`	No
`max_results`	No

Output Schema

Name	Required	Description	Default
`total`	Yes
`offset`	Yes
`results`	Yes
`truncated`	Yes
`error_count`	No
`max_results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.37.0Oct 24, 2026

changedOutput schema / $defs / AdrSummary / description

Previous value: -"One line of ``list_adr`` tool output (plan §8, §9a).\n\nParameters\n----------\nid:\n    The document's specmgr-assigned identifier, or ``None`` if the file\n    has not been assigned one yet (e.g. hand-authored without the\n    ``id`` frontmatter key -- plan §9a).\ntitle:\n    The ADR's ``# {title}`` H1.\nstatus:\n    The ADR's ``frontmatter.status`` value, verbatim.\nref:\n    The document's extensionless base name (e.g.\n    ``\"<uuid>-a-title\"``), deliberately *not* a filename or path --\n    callers must not read this off disk themselves, only pass it to\n    ``get_adr``/``specmgr://adr/{id}`` alongside (or instead of) ``id``.\n    Named ``ref`` rather than ``filename`` precisely to avoid inviting\n    direct filesystem access."New value: +"One line of ``list_adr`` tool output.\n\nParameters\n----------\nid:\n    The document's specmgr-assigned identifier, or ``None`` if the file\n    has not been assigned one yet (e.g. hand-authored without the\n    ``id`` frontmatter key).\ntitle:\n    The ADR's ``# {title}`` H1.\nstatus:\n    The ADR's ``frontmatter.status`` value, verbatim.\nref:\n    The document's extensionless base name (e.g.\n    ``\"<uuid>-a-title\"``), deliberately *not* a filename or path --\n    callers must not read this off disk themselves, only pass it to\n    ``get_adr``/``specmgr://adr/{id}`` alongside (or instead of) ``id``.\n    Named ``ref`` rather than ``filename`` precisely to avoid inviting\n    direct filesystem access."

First observedv0.36.0Oct 17, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses the configured base directory, the default page size of 25, a hard cap of 100, and that out-of-range values are clamped rather than errored. It does not state result ordering, whether non-ADR files in the directory are skipped, or the read-only/no-side-effect guarantee explicitly.

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

Conciseness5/5

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

Four dense sentences with no filler; the payload and scope come first, then the ref caveat, then paging limits. Every clause conveys information an agent needs before calling.

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?

An output schema exists, so return-value explanation is correctly omitted, and the description covers the two real risks of a paged list tool: page sizing and out-of-range behavior. Missing only minor operational context such as sort order and how to detect that more pages remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it largely does: both parameters are described as paging controls with a stated default (25) and cap (100) plus a clamping rule. It still doesn't say whether offset is 0-based or counted in records versus pages, and the nullable/default-null typing is left to the schema.

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 states the exact payload (ids, titles, statuses, refs), the source (ADRs in SPECMGR_ADR_DIR), and the paging nature ('one page at a time'), which unambiguously separates it from get_adr. It also pre-empts a likely confusion by defining 'ref' as an opaque identifier rather than a filename.

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?

It gives a clear condition for use ('for context before addressing one by id') and explicitly routes the agent to get_adr when it has a ref instead of an id. It stops short of stating any when-not condition (e.g., repos too large to enumerate, or when the id is already known and a direct get_adr would be cheaper).

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

Deploy Server