goal_add

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

With no annotations, the description carries the full behavioral burden and does well: it explains progressive elaboration (title-only, draft status for vague nodes), that a partial brief is rejected at the schema level, and that a work_item without a brief receives a `hint` containing the template. It does not disclose permissions, idempotency, or the shape of the response, which keeps it below a 5.

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 critical action and the 'only title required' rule are front-loaded, and every later sentence adds operational detail. The long trigger sentence with multi-lingual example utterances is heavier than typical but the examples are functional for matching, so the cost is justified rather than wasteful.

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 16-parameter create tool with no annotations and no output schema, the description covers the core workflow well and flags the side behavior (hint generation) an agent would otherwise miss. It stops short of describing what is returned (e.g. the new node id) or permission requirements, which are the remaining gaps.

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 description coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it explains the mental model behind only-title-required, the draft default for vague nodes, and the consequence of omitting brief. The restating of kind/status/origin values adds little beyond the schema, but the progressive-elaboration framing is real added value.

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 opening sentence gives a specific verb+resource ('Add a node to the goal graph') and immediately frames it as a progressive-elaboration create operation, which cleanly separates it from read/advance siblings like goal_list, goal_frontier, and goal_advance. An agent knows exactly what this tool produces without opening the schema.

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?

It gives an explicit trigger ('when a user asks you to remember or hand off a piece of work for later'), concrete example utterances, and an explicit exclusion ('Only call when the request is genuinely about work to track; ignore unrelated casual questions'). This is a rare case where when-to-use and when-not-to-use are both stated, so the only missing element is a named alternative tool.

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