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

With no annotations, the description carries full burden. It discloses write operation ('Replace'), clearing behavior ('or clear with empty'), and authorization nuance ('first use may require a manager's approval; a from-now-on approval makes future calls seamless'). Lacks details on idempotency, error handling, or rate limits, but sufficient for a straightforward set operation.

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?

Two concise sentences plus a bracket note with front-loaded main action. Every sentence serves a purpose: main action, usage guidance, approval context. No unnecessary words.

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 fully covers the tool's purpose, scope, parameters (via schema), and usage context including approval tiers. Complexity is low, so no 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 coverage is 100%, so baseline of 3. Description adds clarity for cos_preferences: 'Full preferences text (≤2000 chars). Empty string clears.' This adds value beyond schema. No additional info for companyId. Overall, description adds marginal value but not significantly beyond the schema.

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 verb 'Replace' with the resource 'THIS operator's full CoS preference block' and distinguishes it from partial updates (append) by explicitly saying 'full rewrite'. It contrasts with get_cos_preferences (read) and append_cos_preference (partial update) among siblings.

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?

Explicitly states when to use: 'when they want a full rewrite of saved preferences.' It also clarifies scope ('Per user_id only — not a global product prompt edit') and includes approval notes for write-tier. However, no explicit mention of when not to use or direct sibling name, but context is clear.

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