A document publishing and project design management system with CLI support
Chronicon exposes 16 tools with basic descriptions and partial schemas. Most tool descriptions are under 50 characters and lack actionable context (e.g., 'Authenticate request using headers' does not explain when to call it or what it returns). Input schemas are present but incomplete: many parameters lack type definitions beyond 'object', and descriptions are minimal. No output schemas are documented. Error handling is absent, no guidance on retryability, user-fixable errors, or recovery paths. Tool naming is reasonable (verb_noun pattern) but compositions like 'authenticate' + 'readPublicProfile' suggest multi-step workflows that could be simplified. No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels (READ_ONLY, WRITE, DESTRUCTIVE). Parameter descriptions are generic ('Authenticated principal', 'HTTP request headers') without explaining what fields are required or how to construct them.
Accept an invitation by ID and type
Approve CLI authorization request
Authenticate request using headers
Create a new API key
Exchange CLI credentials for token
List API keys for authenticated user
Load library for a specific project
Publish a new document
No output schemas documented. LLMs cannot infer what fields to expect from tool responses, forcing them to guess at downstream field names and breaking tool composition chains.
Parameter descriptions are generic placeholders ('Authenticated principal', 'HTTP request headers') without explaining required fields, format, or how to construct them. LLMs cannot determine what to pass.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 30 | 2026-07-28+ | v2 |
Read cached library for authenticated user
Read a document by ID with optional revision
Read an invitation by ID and type
Read the public profile of an authenticated user
Revoke CLI token
Revoke an API key by ID
Update a document by ID
Update the public profile of an authenticated user
Tool descriptions are under 50 characters and lack context. 'Authenticate request using headers' does not explain when to call it, what it returns, or what happens on failure. Descriptions should be 50 - 200 chars with actionable context.
No tool annotations (readOnlyHint, destructiveHint, idempotentHint) despite clear risk levels declared (READ_ONLY, WRITE, DESTRUCTIVE). LLMs cannot determine which tools are safe to retry or have irreversible side effects.
No error handling guidance. Tools do not document retryability, user-fixable errors, or recovery paths. LLMs cannot self-correct on failures.