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

Annotations declare destructiveHint=true, and the description adds substantial context beyond that: no money moves, the trade only activates once both sides confirm, confirmation is irreversible, and the error path leaves state unchanged. This is exactly the kind of behavioral information annotations cannot convey.

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 the trigger condition, then consequences, then the caution, then the failure mode. Every sentence earns its place with no redundancy.

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 destructive mutation with an output schema, the description covers the trigger, the effects, irreversibility, and the error path. Return values need not be explained given the output schema, so nothing essential is missing.

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?

Only one parameter with 100% schema description coverage, so the schema already carries its meaning. The description adds no syntax or format details for handshake_id, so the baseline of 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?

States a specific verb (confirm) and resource (the user's side of a Handshake) with scope, and implicitly distinguishes itself from get_handshake (the read used to check preconditions) and complete_handshake. An agent can identify what this does without opening the schema.

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?

Gives an explicit precondition (use when get_handshake reports payment.state = 'covered'), an explicit exclusion (if a fee is owed, it errors and changes nothing), and names the sibling to consult. Nothing is left to inference.

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