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

Annotations only supply the safety/idempotency flags; the description adds the load-bearing behaviors: owner-level authorization required, the record is visible/revisable/removable by the person, and the agent must not invent or infer a hunch. The 'NEW' framing also matches idempotentHint=false coherently.

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?

Four tightly packed sentences, front-loaded with the core action and constraints, with the alternative tool named last. No filler or restatement of the title.

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?

An output schema exists, so return values need not be described. Between the description (auth, naming, confirmation rule, alternative) and the schema (8 params, enums, ranges), an agent has everything needed to call it 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 already 88%, so the baseline is 3, but the description adds real semantics beyond it: a naming convention for situational axes ('When <situation>') and a constraint that 'pole' must reflect what the person actually said, not a model inference. The by/editToken/modelId parameters remain schema-documented only.

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 and resource — recording a newly confirmed hunch as a custom axis added to the person's model — and explicitly frames it as NEW versus an unanswered prompt. It is clearly distinguishable from suggest_question and read_model 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.

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

Gives the selecting condition for both directions: use this when the person has just confirmed an answer, use suggest_question instead if they haven't answered yet. It also states prerequisites (owner-level trust via OAuth or editToken) up front.

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