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

With no annotations, the description carries the full burden, and it does disclose the key consequences: notifications to both MM and the buyer and the start of the inspection window (a time-bound, likely consequential state transition). It omits reversibility (can a delivery mark be retracted?), failure modes, permission/token requirements, and what proof is mandatory per deal type.

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?

Three short sentences, front-loaded with the action and audience, followed by proof requirements and the downstream effect. Minimal waste; the only slight inefficiency is that the proof list is packed into one sentence without mapping parameters separately.

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 six-parameter mutation tool with no output schema and no annotations, the description covers the essential what, who, and consequence, which is enough to call it safely in the common case. The remaining gaps — milestone_id, the deal token requirement, and retraction behavior — keep it short of fully complete.

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 low (33%), and the description clarifies the intent of three parameters (note, links, tx_hash) including a conditional rule — tx_hash applies to token deliveries. However, milestone_id is undocumented in both schema and description, and the required private deal token is never mentioned, leaving genuine gaps.

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+resource ('Mark delivered', 'Tell MM and the buyer') plus the resulting state change ('Starts the buyer's inspection window'). It is distinguishable from siblings like mm_accept_delivery or mm_add_evidence by the actor ('seller') and the delivery-claim framing, though it never names an alternative explicitly.

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?

Usage is implied rather than stated: an agent can infer this is the seller's step after shipping/token transfer, and the token-hash clause hints at branch conditions. There is no explicit when-not, no prerequisites (e.g. deal token/authentication), and no reference to related tools such as mm_add_evidence or mm_check_delivery_now.

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