Skip to main content
Glama
aethis-mcp

aethis-mcp

Official
by Aethis-ai

aethis_discover_sections

Read-only

Analyse source legislation or guidance text to identify which sections should become separate rule sets. Run before creating projects to confirm section boundaries.

Instructions

Discover the logical sections of source legislation for a domain. Provide the raw text of your source documents (legislation, guidance notes, form instructions). The service analyses the content and identifies which sections should be authored as separate rule rulesets. Run BEFORE creating projects — you need to know the sections before you can create one. Call aethis_refine_sections if sections are missing or incorrectly split.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "domain": "<domain>",
      "sources": "<sources>"
    },
    "name": "aethis_discover_sections"
  }
}

Input Schema

NameRequiredDescriptionDefault
domainYesDomain identifier, e.g. 'uk_citizenship'
sourcesYesSource documents to analyse. Provide the actual text content.
openai_keyNoRetired and refused: OpenAI credentials are not accepted for authoring.
anthropic_keyNoAn Anthropic API key the user explicitly provided for this call. [sensitive — do not echo or log] Deprecated: the raw value is written verbatim to the host's session transcript. Never fill this from the environment.
anthropic_key_envNoOptional. Only honoured when it equals the env var the user configured via AETHIS_ANTHROPIC_KEY_ENV in this MCP server's config; that configured key is used automatically, so this can be omitted. Do not guess a variable name: the server refuses any name the user did not configure.
anthropic_key_keychainNomacOS keychain reference the user created for Aethis: either 'service:account' or just 'account' (service defaults to 'aethis-anthropic-key'). The server reads it via the `security` command at call time.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.23.0
    • changedInput schema / properties / openai_key / description
      Previous value: -"Retired and refused: Aethis LLM tools use Anthropic models only."New value: +"Retired and refused: OpenAI credentials are not accepted for authoring."
  2. First observedv0.22.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true and idempotentHint=false, so safety is covered. The description adds that the service performs content analysis (implying a model-driven, non-deterministic call) and that results may be incomplete or wrongly split, which is what motivates the refine sibling — useful, but it discloses nothing about cost, latency, source-size limits, or whether the analysis is charged per call.

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?

Four short sentences, front-loaded with the purpose and followed by input requirements, ordering, and the fallback tool — no filler. Small deductions for the awkward 'separate rule rulesets' phrasing and the sentence-fragment 'Run BEFORE creating projects', which reads as a note rather than a directive.

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 read-only analysis tool with no output schema, the description tells the agent what the result conceptually is (which sections warrant their own rulesets) and when to escalate to aethis_refine_sections. It does not describe the shape of the returned sections (names, boundaries, confidence), so an agent still cannot anticipate the response format, but nothing needed to call the tool correctly is missing.

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 parameter, including the discouraged anthropic_key and the env/keychain alternatives, is already documented in detail. The description only reinforces the 'sources' parameter by naming acceptable content types (legislation, guidance notes, form instructions), which is a marginal addition over the schema. Baseline 3 applies when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Discover the logical sections of source legislation') and clarifies the output is a decision about which sections become separate rulesets. It does not distinguish itself from the other discover_* siblings (aethis_discover_fields, aethis_discover_rulesets), so an agent must infer the boundary from the domain/source inputs alone.

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 concrete sequencing constraint ('Run BEFORE creating projects — you need to know the sections before you can create one') and an explicit hand-off condition ('Call aethis_refine_sections if sections are missing or incorrectly split'). It stops short of saying when this tool is the wrong choice relative to the field- and ruleset-discovery siblings, so the around-the-tool guidance is complete but the lateral guidance is not.

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