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

Annotations only declare readOnlyHint=false, so the description carries the rest and does so richly: 'not safe to repeat blindly' (idempotency warning), suspend seals the chain head at once (irreversibility), plain text is refused and locking/hashing require an external program, and modifications must disclose their prompt. This is exactly the beyond-annotations behavioral context an agent needs before a mutating call.

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

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

Purpose and write-safety warning are front-loaded, which is good, but the middle is a dense run-on kind list packed with em-dashes and parentheticals. The cryptic '(5530, from 578)' fragments do not obviously earn their place. It is information-dense rather than wasteful, but scannability suffers.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter mutation with no output schema and no other annotations, the description covers the required hash/locked workflow, the kind semantics, the external-tool prerequisite, and write safety. What it omits is the return shape on success (e.g., an id) and behavior on validation failure, so it is nearly but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, and the description adds real semantics for the trickiest parameters: body_hash is the sha-256 the registry never sees, body_locked is the same text locked to a key the caller holds, and the supersedes/contradicts/revises relation requires prompted_by. It leaves secret, ref_id, anchor, and unresolved largely to the schema, so it is additive rather than exhaustive.

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

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

States a specific verb+resource (write a journal entry) and frames it as the 'private continuity organ', which implicitly separates it from the read/review siblings. It enumerates the six kinds concretely, but never explicitly names journal_read or journal_review as the read-side alternatives, so sibling differentiation is implied rather than stated. The parentheticals (5530, from 578) add noise without clarifying purpose.

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

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

Gives substantial when-to-use guidance via the kind taxonomy: core for identity, suspend for wake-out notes, renewal when purpose changes, break after failed verification, custody when the key changes. It also states prerequisites (a program via GET /tools/envelope.mjs) and the rule that entries with a relation must state what prompted them. It stops short of contrasting with the journal_read/journal_review siblings explicitly.

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