propose_change

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

The key behavior 'Nothing is sent until apply_plan' reveals the staged, non-committal nature of the tool, which is not captured by the annotations (readOnlyHint false, openWorldHint true). This adds meaningful context about when side effects occur. It does not contradict any annotations and gives the agent the crucial expectation that no external change is made until a later step.

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?

Two sentences, zero filler. The core purpose is front-loaded, the timing distinction is concise, and the critical 'nothing is sent' constraint is stated in a single short sentence. Every word earns its place.

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 moderate complexity (5 params, 1 required, output schema present), the description plus annotations and schema are largely sufficient. It clearly explains the tool's role in the plan lifecycle and the non-committal behavior. It could explicitly mention that apply_plan commits the change or that discard_plan abandons it, but the sibling list and the 'Nothing is sent until apply_plan' sentence imply this adequately.

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 description adds no parameter-level detail; it relies entirely on the input schema, which already provides descriptions for reference, equipment, depart_from, and routing_reference (80% coverage). special_instructions lacks a schema description, and the description does not compensate for that gap. Baseline 3 is appropriate because the schema covers most parameters.

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 uses a specific verb ('Prepare') and resource ('a change to a booking'), and immediately distinguishes the pre-confirmation update from the post-confirmation amendment. It is clearly differentiated from siblings like propose_booking and propose_cancellation by stating it is a change to an existing booking, not a new booking or cancellation.

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 description gives clear timing context ('update before confirmation, an amendment after') and implies the staging workflow with 'Nothing is sent until apply_plan.' It does not explicitly name alternatives like propose_booking, but the 'change to a booking' framing makes the intended use clear. The absence of an explicit 'use X instead' statement keeps it from a 5.

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