biz.dfch.SpecMgr

Overview Schema Source Related Servers Discussions Admin

List Standard Operating Procedures

list_sop

Lists Standard Operating Procedures with IDs, titles, statuses, and refs one page at a time, so you can choose one before retrieving it by ID. Supports glob filters, paging, and language selection.

Instructions

Ids, titles, statuses, and refs of Standard Operating Procedures in the configured SOP base directory, 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 it with the get_sop tool instead. An optional glob pattern (e.g. 'dead*') filters the listing to the Standard Operating Procedures whose id matches it, case-insensitively; glob=None (the default) lists everything, and an empty string matches nothing. max_results/offset control paging (default page size 25, capped at 100); out-of-range values are clamped, not errored. The optional language parameter (default 'en') selects the directory scanned: omitted/'en' = the flat docs/sop/ directory (the default behavior, unchanged); any other ISO 639-1-shaped lowercase two-letter code (e.g. 'de') = only that language's docs/sop/{language}/ subdirectory, listing exactly the existing variants of that language (there is deliberately no 'all languages' mode). The language is shape-validated before any file access (an invalid-shaped value 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.

Input Schema

Name	Required	Default
`glob`	No
`offset`	No
`language`	No	en
`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 changedv0.38.0Nov 2, 2026

addedInput schema / properties / language

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

First observedv0.36.0Oct 17, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations supplied, the description carries the full behavioral burden and does so: default page size 25, cap at 100, out-of-range values clamped rather than errored, and validation ordering (language shape-validated before any file access, missing heading-mapping table rejected up front). It also discloses that an invalid-shaped language raises ValueError 'like an invalid id', which is exactly the failure-mode detail an agent needs.

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

Conciseness4/5

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

Purpose and the get_sop hand-off are front-loaded, and every sentence adds distinct information. The single semicolon-chained paragraph is dense and would scan better split by parameter or bulleted, but there is no padding or repetition.

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?

Covers purpose, paging, filtering, error behavior, and per-language directory semantics for a 4-parameter read tool. Return values need not be described because an output schema exists, so the remaining surface an agent needs before calling is fully covered.

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 coverage is 0%, so the description must compensate and does for all four parameters: glob (case-insensitive id match, example 'dead*', glob=None vs empty string matching nothing), offset/max_results (paging with defaults and clamping), and language (default 'en' = flat docs/sop/, other ISO 639-1 codes = docs/sop/{language}/). This is substantially more than the bare schema types convey.

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 concrete verb+resource and enumerates what is returned ('Ids, titles, statuses, and refs of Standard Operating Procedures'), scoped to the configured SOP base directory. It immediately differentiates the listing from the by-id retrieval path by naming get_sop for opaque 'ref' handles.

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 a clear use context ('for context before addressing one by id') and routes the 'ref' case to the get_sop sibling instead. It also rules out an 'all languages' mode and explains per-language scoping, but never states a positive when-not-to-use case (e.g. when parse_sop or get_sop is preferable for bulk content).

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

Deploy Server