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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description earns its keep on top of that by naming the blast radius (buyer-quoted prices change in live mode) and the guardrails that bound it (exploration band, never below cost, price guardrails). It also covers reversibility ('null goes back to the default') and auth scope. No contradiction with the destructive/idempotent hints.

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 tight sentences, front-loaded with what the tool sets before moving to risk, update semantics, and permissions. Nothing is padding, though the opening sentence carries three clauses and could be split for faster scanning.

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 three-parameter, fully-optional mutation with rich schema text and annotations, the description covers purpose, risk envelope, merge semantics, and authorization. The only gap is the absence of any statement about the response, which matters slightly given there is no output schema.

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 the per-parameter enums and defaults are already documented and the baseline would be 3. The description adds a genuinely new rule not spelled out per-param: omitted fields keep their saved value, while explicit null resets to default — a critical distinction for a tool with zero required parameters.

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 opens with a specific verb and resource and enumerates exactly what is configured (mode, live model, readable request fields), so an agent knows the surface area immediately. It stops short of naming the neighbours it must not be confused with (set_learned_pricing, set_price_exploration, set_price_guardrails, get_buyer_aware_pricing), so sibling differentiation is left implicit.

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?

Prerequisites are stated concretely: a Last Price credential with routing write scope, or an owner/admin when acting from the dashboard. It also explains the consequence of 'live' (quoted buyer prices change) and the partial-update rule, which tells the agent when this call is safe to make. It gives no explicit when-not-to-use or alternative tool, which keeps it below a 5.

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