biz.dfch.SpecMgr

Overview Schema Source Related Servers Discussions Admin

Get decision

get_dec

Read and parse a full decision document by id to retrieve its frontmatter and body, with optional language variants, raw text, offset/limit windows, or numbered lines.

Instructions

Read, parse, and return a full decision document (frontmatter and body) by its id. The optional language parameter (default 'en') selects the language variant to read: omitted/'en' = the flat docs/dec/ document, exactly the default behavior; any other ISO 639-1-shaped lowercase two-letter code (e.g. 'de') = that language's variant at docs/dec/{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. 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) -- for a language variant, against list_dec(language=...) on the same file. 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_dec -- strip the "<n>: " prefix from each line first (it is likewise never a valid edit old_str).

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"
+}

Changed1 schema field changedv0.37.0Oct 24, 2026
- addedOutput schema / $defs / DecFrontmatter / properties / status / enum
```
Added value: +[
+  "accepted",
+  "deprecated",
+  "draft",
+  "proposed",
+  "rejected",
+  "superseded"
+]
```
First observedv0.36.0Oct 17, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: language variants are shape-validated before any file access, missing heading tables are rejected up front with actionable ValueErrors, parse failures return a ParseFailureResult rather than raising, and out-of-range offset/limit clamp to an empty string. It even documents cross-tool invariants (error text byte-identical to list_dec, numbered output must be stripped before feeding update/create_dec/edit).

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?

Core purpose is front-loaded, but the body is a single ~330-word paragraph of chained em-dashes and parentheticals that is hard to scan. Some content is repeated ('before any file access' appears twice) and the ADR hash reference is noise for an invoking agent, though the underlying behavioral facts do earn their place.

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 6-parameter, 0%-schema-coverage, unannotated tool this is close to complete: modes, validation ordering, error shapes, clamping, and cross-tool constraints are all covered, and the existing output schema relieves it of explaining return values. The only substantive omission is the accepted format of `id`.

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 supply all parameter meaning, and it does for language (default 'en', docs/dec vs docs/dec/{language}/), raw, offset (1-based, default 1), limit (default through end), and numbered ("<n>: " prefix, absolute numbering that survives windowing). The required `id` parameter gets only error behavior (path-injection/wrong format → ValueError) but never states the expected id format, leaving one gap.

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?

Opens with a precise verb+resource+scope: 'Read, parse, and return a full decision document (frontmatter and body) by its id.' It also makes the boundary against related tools explicit by naming list_dec, update, create_dec and edit and describing how their outputs/inputs interact with this tool's.

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?

Gives clear conditional guidance for the main modes: use raw=True for verbatim body text, raw=False for the parsed structured model, and offset/limit/numbered only with raw=True (with the stated ValueError otherwise). It never states the plain 'use this instead of list_dec when you know the id' routing rule, so the sibling-selection guidance is implied rather than spelled out.

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

Deploy Server