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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds substantial behavioral context beyond these: it specifies the selection algorithm (one best-scored open venue per slot), the availability check (every stop open on the given date), the inclusion of a bookable experience, and the behavior of also listing itinerary titles. This is rich, non-redundant behavioral disclosure that helps the agent predict outcomes.

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 description is a single, information-dense sentence that front-loads the core action and criteria, then appends the alternative guidance. There is no filler or repetition; every clause adds value. It is appropriately sized for the tool's complexity.

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 complexity (6 parameters, no output schema, no nested objects), the description covers what the agent needs to call it correctly: what it returns (venue-per-slot plan plus a bookable experience and itinerary titles), when to prefer the alternative, and the filters. It does not explain return formats, but the absence of an output schema makes the description's summary of results sufficient.

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 100%, so the schema already documents all six parameters. The description repeats the filter concepts (neighbourhood, dietary need, price tier) but adds no syntax, formatting, or edge-case details beyond what the schema provides. It does not compensate for anything missing, so the baseline 3 is appropriate.

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 states a specific verb ('Compose'), a precise resource ('a food day for one city'), and enumerates the selection criteria (best-scored open venue per slot, filtered by neighbourhood, dietary need, price tier, open on date, plus one bookable experience). It also names the sibling alternative (`itineraries`) and the condition that selects it, making the purpose unambiguous and distinct from the other 9 tools.

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 explicitly says the editorial itineraries are 'the better plan when one exists' and directs the agent to fetch them with `itineraries`. This is an explicit when-to-use/when-not-to-use directive with a named alternative, exceeding the minimum bar for usage guidance.

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