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

Beyond the annotations (readOnly=false, openWorld=true, idempotent=false, destructive=false), it describes the mutation's effect on the model, visibility/editability/removability, and the auth path (owner OAuth or editToken). It also establishes data-fidelity constraints ('Never invent or infer a hunch they didn't confirm'). No contradiction with annotations.

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?

All five sentences carry distinct, decision-relevant information: purpose+effects, auth, data fidelity, naming, and the alternative tool. It is compact (~75 words) and front-loaded with the core purpose, with no filler or redundant content.

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 write tool with 8 parameters, this description covers the operational context fully: what qualifies as input, required authority, how to format names, and which sibling to use instead. Because an output schema exists, not detailing return values is acceptable. The only minor omission is not explicitly saying what happens if a hunch with the same name already exists, but idempotentHint=false and 'NEW' imply a new axis.

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?

With 88% schema coverage, the baseline is high, and the description adds value by prescribing the naming convention for situational axes ('When <situation>') and reinforcing the meaning of pole ('what the person SAID') and editToken (owner-level alternative). It doesn't address 'confidence' or 'by', but the schema already documents those well.

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 clearly identifies the operation: recording a NEW hunch/custom axis that the person just confirmed, with key traits (visible, revisable, removable). It differentiates from siblings by emphasizing 'just confirmed' and explicitly names suggest_question as the alternative, so the agent knows exactly what this tool does and how it differs.

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?

States the core precondition ('just confirmed in conversation') and the authority requirement (OAuth as owner or editToken). It gives an explicit exclusion and alternative: 'If they haven't answered yet, use suggest_question instead' and forbids inventing/inferring unconfirmed hunches, providing clear when-to-use and when-not-to-use guidance.

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