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

Annotations only declare the safety profile (not read-only, non-destructive, non-idempotent). The description adds substantial behavior beyond that: a simulation-first proposal, an explicit needs_input response contract, that answers are remembered per product, and where weight/dimensions/parcel/COD values are sourced. These are exactly the traits an agent needs and none are in the annotations.

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 purpose is front-loaded in the first clause, and sentences are dense with useful detail rather than filler. It is long, but each sentence carries an operational fact (sourcing, confirmation, needs_input loop); only the closing shop note is low-value.

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 15-parameter mutation tool with an output schema, the description covers the flow, data sourcing, simulation, and error/re-try contract well. The remaining gap is per-parameter meaning for the ~80% of parameters left undocumented in the 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 description coverage is only 20% across 15 parameters, so the schema does not carry the load. The description explains the provenance of several values (receiver, COD amount = 0 when paid online, pickup address, weight/dimensions/parcels from product data) which helps, but many parameters (envelopes, observation, sender_*, is_oversize, width/height/length) get no semantic treatment beyond their names.

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?

States a specific verb (Propose) and resource (AWB / shipping label) scoped to one order through the marketplace's courier accounts. This clearly distinguishes it from sibling awb_get, which retrieves rather than proposes.

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 two-step flow is spelled out: propose/simulate first, and the AWB is only issued and pickup requested after the seller approves. It also directs the agent to re-call with plain-words answers when the response is needs_input. It does not explicitly name a competing sibling or exclusion cases, but the operational context is clear.

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