journal.write

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

With no annotations provided, the description carries the full behavioral burden. It discloses side effects (creates the journal file if missing), idempotency (same file_id per calendar day), storage semantics (agent_note event in Layer 1 for notes), and return values for every kind. This is thorough for a mutation tool, covering both effects and results.

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?

The description is dense but efficient. It opens with the core purpose, then uses a clear kind-by-kind breakdown with inline return types. While slightly long, every sentence carries actionable information, and the structure mirrors the enum options, aiding comprehension. No filler or redundancy.

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?

Given no output schema, the description must specify return values, and it does for each kind: {file_id} for append, {ok, recorded_at} for note and intent. It also covers creation behavior, daily idempotency, and how notes surface in distillation. With 5 parameters and 3 conditional modes, this is a complete operational spec for an agent to call correctly.

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 100%, so baseline is 3, but the description adds substantial semantic value: it explains the meaning of each kind, which fields are required conditionally, and the behavioral consequences of each choice. For instance, it clarifies that 'intent' needs 'summary' while 'append'/'note' need 'text', and explains how 'intent' affects distillation. This goes well beyond the schema's generic field descriptions.

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?

The description opens with a precise verb and resource: 'Write one event to the current project's journal.' It then enumerates three distinct kinds (append, note, intent) with concrete behaviors and return payloads. This clearly differentiates it from sibling journal tools like journal.distill or journal.status, which are read/aggregation operations, and from files.write, which targets a different storage layer.

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?

The description gives explicit when-to-use guidance for each kind, e.g., 'use when the user redirects what you're working on' for intent, and specifies conditional required fields. It does not explicitly state when not to use this tool versus alternatives, but the sibling set makes the write purpose obvious, and the kind-specific instructions are unambiguous.

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