biz.dfch.SpecMgr

Overview Schema Source Related Servers Discussions Admin

Get verification case record

get_vcr

Retrieve a full verification case record document by id, returning parsed frontmatter and body. Use raw mode to read body text verbatim, optionally windowing lines by offset and limit.

Instructions

Read, parse, and return a full verification case record document (frontmatter and body) by its id. Pass raw=True to return the frontmatter-stripped body text verbatim instead. With raw=True, optional read-style offset/limit window the raw read: offset (1-based, default 1) is the first body line to return, limit (line count, default through end of body) how many; out-of-range values clamp (offset > N returns the empty string), and coordinates with raw=False raise ValueError. A document that exists but fails to parse returns a ParseFailureResult (error/path/id) instead of raising; its error text is byte-identical to the domain's own list tool's failed-row error for the same file (identical field path and cause, including the trailing pydantic documentation line; ADR 9080b37c-82b3-4f63-81f1-79641d0bf14c). An invalid id (path-injection attempt or wrong format) is also a ValueError, raised before any file access. With raw=True, an optional numbered=True prefixes every returned body line with its 1-based absolute body-line number in the "<n>: " form (plain decimal, no padding) -- under offset/limit windowing the numbers start at the clamped offset and never restart at 1, so a number seen in the output can be fed straight back into the generic update tool's offset. numbered is meaningful only with raw=True: combining it with raw=False raises ValueError (like offset/limit), and a numbered read of a document that fails to parse returns the ParseFailureResult described above, never numbered text. Numbered output must never be fed back verbatim into content for update or create_vcr -- strip the "<n>: " prefix from each line first (it is likewise never a valid edit old_str). The optional language parameter (default 'en') selects the language variant to read: omitted/'en' = the flat docs/vcr/ document, exactly the default behavior; any other ISO 639-1-shaped lowercase two-letter code (e.g. 'de') = that language's variant at docs/vcr/{language}/ (the EN source's exact basename). The language is shape-validated before any file access (a path-injection-shaped payload is a ValueError, like an invalid id), and a shape-valid language without a packaged heading-mapping table is rejected up front with an actionable ValueError, also before any file access. A raw=True read of a variant returns the variant's on-disk body verbatim (translation preserved); a raw=False read parses it through the variant's heading table, so the structured model holds canonical heading text. The ParseFailureResult error of a broken variant is byte-identical to list_vcr(language=...)'s failed row for the same file.

Input Schema

Name	Required	Default
`id`	Yes
`raw`	No
`limit`	No
`offset`	No
`language`	No	en
`numbered`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.38.0Nov 2, 2026

addedInput schema / properties / language

Added value: +{
+  "default": "en",
+  "title": "Language",
+  "type": "string"
+}

Changed3 schema fields changedv0.37.0Oct 24, 2026

changedOutput schema / $defs / AcceptanceCriterion / description

Previous value: -"`### AC-NNN (Method): <criterion text>` under `## Acceptance Criteria` -- one verification criterion.\n\nThe number, method, and criterion text all live in the heading itself\n(e.g. `### AC-001 (Test): The revoke endpoint returns 204 within 1s`),\nconstrained by the regex `@alias` above and enforced by `match_alias`\n(`re.fullmatch`) at parse time -- a missing/out-of-range/malformed\nnumber, an unknown method word, or a title-less heading all fail the\nparse eagerly (REQ-003). AC numbers need not be contiguous (gaps are\nallowed, numbers are never renumbered); duplicates are rejected by\n`Vcr`'s own after-validator (the `ValidationError` channel, mirroring\nDEC's `Decision._validate_option_numbers_unique`).\n\nUnlike DEC's `Option`/RSK's `Probability`/`Impact` (all *leaf* sections\nwith zero other declared fields, so their own `.text` computed property\nreturns the *complete* extent verbatim, heading marker and any body\ntext both included), this class declares two other fields\n(`description`, `test_steps`), making it a *composite* section: its own\n`.text` therefore returns only the heading's own inline content (marker\nstripped, body text excluded -- see `MarkdownSection.text`'s composite\nbranch). `number`/`method` below are matched against that heading-only\n`.text` directly, not `.text.splitlines()[0]` -- the DEC/RSK idiom's\nexact mechanics don't apply verbatim here because of this leaf/composite\ndifference, even though the underlying idea (compute a value from the\nretained heading text via a private module-level compiled regex) is the\nsame. A consequence: an `AcceptanceCriterion`'s body may contain nothing\nbesides an optional free-form `description` paragraph followed by an\noptional `#### Test Steps` -- both independently optional (e.g. one\ncriterion may carry only a description, another only `Test Steps`,\nanother both, another neither), in that fixed declaration order.\n\nParameters\n----------\ndescription:\n    The lead paragraph directly under the heading -- free-form prose\n    elaborating on the criterion beyond what fits in the heading\n    itself (mirrors `MoreInformation`'s \"free-form, no fixed format\"\n    tone). Optional; independent of `test_steps`.\ntest_steps:\n    `#### Test Steps` sub-section (a numbered verification procedure).\n    Optional; independent of `description`.\nnumber:\n    Computed. The criterion's 3-digit number (e.g. `1` for\n    `### AC-001 (Test): ...`). Never stored separately -- derived from\n    the retained heading text.\nmethod:\n    Computed. The closed DTAIS method word carried by the heading\n    (e.g. `\"Test\"` for `### AC-001 (Test): ...`), exactly as written\n    (not lowercased/normalized). Never stored separately -- derived\n    from the retained heading text."New value: +"`### AC-NNN (Method): <criterion text>` under `## Acceptance Criteria` -- one verification criterion.\n\nThe number, method, and criterion text all live in the heading itself\n(e.g. `### AC-001 (Test): The revoke endpoint returns 204 within 1s`),\nconstrained by the regex `@alias` above and enforced by `match_alias`\n(`re.fullmatch`) at parse time -- a missing/out-of-range/malformed\nnumber, an unknown method word, or a title-less heading all fail the\nparse eagerly (REQ-003). The method word is one of the five DTAIS words:\n`Demonstration`, `Test`, `Analysis`, `Inspection`, `Special` (the\n`specmgr://dtais` vocabulary). AC numbers need not be contiguous (gaps are\nallowed, numbers are never renumbered); duplicates are rejected by\n`Vcr`'s own after-validator (the `ValidationError` channel, mirroring\nDEC's `Decision._validate_option_numbers_unique`).\n\nUnlike DEC's `Option`/RSK's `Probability`/`Impact` (all *leaf* sections\nwith zero other declared fields, so their own `.text` computed property\nreturns the *complete* extent verbatim, heading marker and any body\ntext both included), this class declares two other fields\n(`description`, `test_steps`), making it a *composite* section: its own\n`.text` therefore returns only the heading's own inline content (marker\nstripped, body text excluded -- see `MarkdownSection.text`'s composite\nbranch). `number`/`method` below are matched against that heading-only\n`.text` directly, not `.text.splitlines()[0]` -- the DEC/RSK idiom's\nexact mechanics don't apply verbatim here because of this leaf/composite\ndifference, even though the underlying idea (compute a value from the\nretained heading text via a private module-level compiled regex) is the\nsame. A consequence: an `AcceptanceCriterion`'s body may contain nothing\nbesides an optional free-form `description` paragraph followed by an\noptional `#### Test Steps` -- both independently optional (e.g. one\ncriterion may carry only a description, another only `Test Steps`,\nanother both, another neither), in that fixed declaration order.\n\nParameters\n----------\ndescription:\n    The lead paragraph directly under the heading -- free-form prose\n    elaborating on the criterion beyond what fits in the heading\n    itself (mirrors `MoreInformation`'s \"free-form, no fixed format\"\n    tone). Optional; independent of `test_steps`.\ntest_steps:\n    `#### Test Steps` sub-section (a numbered verification procedure).\n    Optional; independent of `description`.\nnumber:\n    Computed. The criterion's 3-digit number (e.g. `1` for\n    `### AC-001 (Test): ...`). Never stored separately -- derived from\n    the retained heading text.\nmethod:\n    Computed. The closed DTAIS method word carried by the heading\n    (e.g. `\"Test\"` for `### AC-001 (Test): ...`), exactly as written\n    (not lowercased/normalized). Never stored separately -- derived\n    from the retained heading text."

addedOutput schema / $defs / AcceptanceCriterion / pattern

Added value: +"^AC-(\\d{3}) \\((Demonstration|Test|Analysis|Inspection|Special)\\): .+$"

addedOutput schema / $defs / VcrFrontmatter / properties / status / enum

Added value: +[
+  "approved",
+  "complete",
+  "draft",
+  "progress"
+]

First observedv0.36.0Oct 17, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses that unparseable documents return a ParseFailureResult rather than raising, that invalid ids and path-injection payloads raise ValueError before any file access, that language is shape-validated and rejects untabled codes up front, and which parameter combinations raise ValueError. It even guarantees error-text byte-identity with list_vcr's failed row, which is unusually precise behavioral disclosure.

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

Conciseness3/5

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

Purpose and the raw/windowing semantics are front-loaded, which is good, but the description is one dense run-on paragraph with repeated digressions. The byte-identical ParseFailureResult claim is restated three separate times, and an embedded ADR UUID adds length without decision value for an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given six parameters, zero schema coverage, and a mutation-adjacent read surface, the description covers everything an agent needs to call it correctly, including failure modes and the numbered-output pitfall. An output schema exists, so the description is not obliged to explain return shapes further.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must compensate for all six parameters, and it does: `offset` is 1-based and clamps out-of-range, `limit` defaults to end-of-body, `numbered` uses an unpadded `"<n>: "` prefix that continues from the clamped offset, and `language` defaults to 'en' with a documented variant path layout. Only `id` is left thin (format is only described negatively, as "wrong format" raising ValueError).

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 first sentence names a specific verb pair and resource: "Read, parse, and return a full verification case record document (frontmatter and body) by its id." It is immediately distinguishable from sibling list_vcr (enumeration), parse_vcr (parsing only), and the read-style variants of other artifact types.

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 clearly routes parameter choices: raw=True for the verbatim body, raw=False for the parsed model, offset/limit only with raw=True, numbered only with raw=True, and language for translated variants. It also warns that numbered output must not be fed back into `update`/`create_vcr` `content` or `edit` `old_str`, which is genuine anti-pattern guidance. The one gap is that it never explicitly contrasts the tool with parse_vcr for the same record, leaving that sibling choice implicit.

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

Deploy Server