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

Annotations already establish readOnly/destructive safety, but the description adds a genuine behavioral quirk: surprises render as "Surprise" with only times and the agent is told not to probe or guess. That is information an agent could not get from annotations or schema and directly prevents a misuse.

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 sentences with no filler: return shape first, default scoping second, surprise caveat last. Each sentence carries distinct decision-relevant information.

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?

An output schema exists, annotations cover the safety profile, and the description covers the non-obvious case (surprise activities) that the schema cannot express. Nothing needed to call this correctly 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?

Schema coverage is 100%, so the baseline is 3; the description earns above baseline by explaining the semantic consequence of `person` (defaults to the current user's own plan) rather than just repeating the parameter's type. It does not add format details, but the schema already supplies those.

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 exactly what is returned: one person's ordered activities on a trip, including lane-specific activities where the group splits. It also clarifies whose plan is fetched by default, so an agent knows the resource and scope 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?

Clearly defines the default case ('The user's own plan unless `person` is given'), which tells the agent when to pass the optional parameter. It does not name alternatives such as get_trip for trip-level structure, so routing guidance is context-complete but not exhaustive.

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