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

The description goes far beyond annotations by disclosing the atomic concurrency guarantee ('two concurrent agent sessions cannot double-allocate the last unit'), the hold TTL defaults and cap ('Default hold TTL 900s (15min), hard cap 3600s (1h)'), and the specific failure reasons (OUT_OF_STOCK, NOT_DELIVERABLE, HOLD_SERVICE_UNAVAILABLE). This adds rich behavioral context that the annotations (readOnlyHint=false, openWorldHint=true) do not provide.

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 dense but every sentence earns its place: core action, workflow context, concurrency rationale, return shape, failure reasons, hint guidance, and TTL policies. It fronts the primary purpose and then layers details logically without redundant wording.

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 the tool's complexity (atomic hold, multiple params, no output schema), the description covers return values on success and failure, the exact failure reason enum, the workflow sequence, and TTL semantics. The only missing piece is a few parameter semantics, but those are partially handled by the schema and the description still provides enough context for correct invocation in the main loop.

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?

The schema has 0% description coverage, so the description must compensate. It adds meaning for deliverTo ('estimates shipping + tax for deliverTo'), productIdHint/shopIdHint (for resolution), and holdTtlSec (via TTL defaults). However, it does not explain skuId, quantity, agentBearer, or consumerAgentKind, leaving those to the schema's minimal type info. This is a partial compensation, not a full one.

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 tool's function: 'Atomically quote price + delivery + reserve stock for a SKU'. It uses a specific verb and resource, and explicitly differentiates itself from siblings by calling it 'the linchpin between discovery (find_inventory) and tender (start_checkout)', making its unique role unmistakable.

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?

It provides explicit usage context by positioning the tool within the consumer-agent loop and tells the agent to pass 'productIdHint + shopIdHint from a preceding find_inventory result'. This gives clear when-to-use guidance and references the exact preceding tool, while also implying the next step (start_checkout).

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