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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value by disclosing the output shape contradiction ('flat ranked candidate list, not structured day slots or a running cost') and the implied post-processing burden on the caller, which annotations cannot express.

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 tight sentences, front-loaded with the triggering condition, then the return-shape caveat, then the caller's responsibility. Every sentence carries information an agent needs and none is repeated from the schema.

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?

With an output schema present, return values need not be enumerated, and the description goes further by warning about the flat-list shape and the absence of a computed cost. With 8 parameters fully documented in-schema, an agent has everything needed to select and invoke this correctly.

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%, including enum meanings, defaults, and the 'family' tag caveat, so the schema does the heavy lifting. The description adds no parameter-level guidance such as how 'pace' interacts with 'days' or how budget bands are applied, so the baseline 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?

The description names a specific trigger ('user wants a multi-day plan for a single city') and a specific deliverable ('flat ranked candidate list of experiences'), then explicitly negates what it is not (structured day slots, running cost). This is far more precise than the siblings like get_city_highlights or get_family_day, which target different scopes.

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?

It gives a clear triggering condition and an important negative constraint (returns raw candidates, not a formatted itinerary), telling the agent it must arrange days and compute totals itself. It stops short of naming sibling alternatives (e.g., get_family_day for single-day family plans), so an agent must infer the boundary from context rather than being routed explicitly.

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