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

Annotations already flag destructive/non-idempotent, but the description goes well beyond them: it explains that the removal is written as a transaction in SkuVault's history, that repeat calls remove again, warns against blind retries, and discloses a 10/min throttle plus the underlying endpoint. This is exactly the mutation risk context an agent needs.

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 dense sentences, mutation semantics and the retry hazard front-loaded, then prerequisites, throttling and endpoint. No filler and nothing buried at the end that an agent needs first.

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 7-parameter destructive mutation with no output schema, the description covers non-idempotency, prerequisites, throughput limits and the underlying route. An agent has everything needed to invoke it correctly and avoid duplicate removals.

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 description coverage is 100%, so every parameter including reason ('must already exist') and serial_numbers ('only for serialized products') is already documented structurally. The description restates those same points rather than adding new semantics, so 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 opens with a specific verb and resource ('remove quantity of a product from a warehouse location') and the 'WRITE:' prefix instantly marks it as a mutation. It is plainly the inverse of skuvault_add_stock, but it never names that sibling explicitly, so differentiation comes from inference rather than a stated contrast.

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?

'do not retry blindly' and 'the transaction reason must already exist' give real operating context, and serialized products needing serial numbers is a clear precondition. However, it never says when to choose this over skuvault_set_stock_quantity (absolute set) or add_stock, and offers no explicit exclusions, so usage is only implied.

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