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

Beyond the destructiveHint annotation, the description discloses the approval workflow (manager approval, from-now-on vs just-once) and the clearing behavior. It does not contradict annotations and adds meaningful behavioral context about permission gates, which is valuable.

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 compact and front-loaded with the core action and usage. The bracketed approval guidance adds essential operational detail without bloat. Minor jargon ('THIS operator', 'card is the yes') slightly obscures but does not warrant a lower score.

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 simple two-parameter write tool with annotations and no output schema, the description covers the main behaviors: replacement, clearing, scope, and approval flow. It could potentially mention that the operation is irreversible or destructive, but the destructiveHint annotation already conveys that.

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% for both parameters, and the schema already describes cos_preferences and companyId. The description only restates that empty clears and the full block is replaced, adding minimal semantic value beyond the schema. Baseline 3 applies.

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 clearly states the action ('Replace THIS operator's full CoS preference block'), the resource scope ('CoS preference block'), and the clear/delete behavior ('clear with empty'). It also distinguishes itself from append_cos_preference by noting 'full rewrite' vs. incremental edits, and from a global product prompt edit via 'Per user_id only'.

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 says 'Use when they want a full rewrite of saved preferences' and explicitly excludes global edits. It adds approval-flow guidance on when to call vs. re-ask in chat. It could be stronger by naming append_cos_preference as the alternative for partial changes, but the full-rewrite framing adequately guides selection.

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