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

Annotations already mark it read-only/idempotent/non-destructive, so the description adds non-obvious behavioral detail: no_cached_data is not 'no offers', prices are package totals in EUR not per person, party_match=false means the 2-adult reference, and a price belongs only to its own date. These caveats are far beyond what the annotations 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?

Every sentence carries a distinct warning or clarification; there is no filler. The core purpose is front-loaded and the caveats are ordered logically from cache semantics to pricing units to date ownership.

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 no output schema, the description carries the full burden of explaining response semantics, and it covers the critical fields (availability_status, cached_at/age_minutes, party_match, best_value_date) and their pitfalls. An agent can interpret rows safely without further guidance.

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 parameters are already documented; the description adds relevant context about party-level totals and window length but does not add per-parameter syntax beyond the schema. The baseline of 3 is appropriate because the schema carries the parameter burden.

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 precise operation: return the lowest cached package total for each departure date in a window, plus best_value_date, for a destination and party. The 'CACHED' and 'window' qualifiers distinguish it from siblings like charter_cheapest and charter_dates without needing their schemas.

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?

'For flexible travellers' gives a clear when-to-use signal, and the explanation that this is cached rather than live tells the agent when it is not appropriate. It stops short of naming a sibling as the live alternative, but the context is strong enough for routing.

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