Skip to main content
Glama
aethis-mcp

aethis-mcp

Official
by Aethis-ai

aethis_review_project

Read-only

Reviews an authoring project against a deterministic rubric, returning scores, per-check evidence, strengths, and one next improvement for advisory, non-blocking skill-building feedback.

Instructions

Review an authoring project against the deterministic authoring-coach rubric and get skill-building feedback. Returns a score, per-check evidence across grounding / process / lifecycle, strengths, and the single highest-leverage next improvement. Advisory only — it never blocks publishing. The deterministic report needs no LLM key; set coach=true (with an Anthropic key) to add an LLM-synthesised coaching narrative on top of the computed checks.

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": {
      "project_id": "<project_id>"
    },
    "name": "aethis_review_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
coachNoAdd an opt-in LLM-synthesised coaching narrative on top of the deterministic rubric. Requires an Anthropic key the user configured (AETHIS_ANTHROPIC_KEY_ENV, anthropic_key_keychain, or anthropic_key). Off by default — the deterministic report needs no key.
openai_keyNoRetired and refused: OpenAI credentials are not accepted for authoring.
project_idYesThe project ID to review
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

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds real signal beyond them: the report is advisory and never gates publishing, the deterministic path needs no LLM key, and the LLM narrative is opt-in and depends on an Anthropic key. What is missing is whether repeated reviews of an unchanged project return stable results, which matters given idempotentHint=false and the word "deterministic" in the description — a mild tension worth stating but not a direct contradiction, since coach mode introduces non-determinism.

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?

Three front-loaded sentences with zero filler: first the action and return contents, then the advisory/non-blocking guarantee, then the key and coach-mode requirement. Each sentence carries distinct information an agent needs.

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?

There is no output schema, and the description compensates by enumerating the report's contents (score, per-check evidence by category, strengths, single top improvement). Combined with the rich, fully documented parameter schema and the safety annotations, nothing essential for correct invocation is absent.

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%, so the baseline of 3 applies; the schema already explains coach, the deprecated anthropic_key, anthropic_key_env, anthropic_key_keychain, and the refused openai_key. The description reinforces the two operating modes (deterministic vs. LLM-narrated) but adds no new format, default, or constraint beyond what the schema already states.

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?

States a specific verb and resource ("Review an authoring project against the deterministic authoring-coach rubric") and even previews the return payload: score, per-check evidence across grounding/process/lifecycle, strengths, and the top next improvement. It also separates itself from the publishing path by declaring "Advisory only — it never blocks publishing," so an agent can place it relative to aethis_publish without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers useful framing (advisory, non-blocking, no key needed by default) and a clear condition for the optional LLM upgrade via coach=true. However, it never says when an agent should call this versus adjacent diagnostic tools such as aethis_explain, aethis_explain_failure, or aethis_decide, leaving the choice to inference.

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