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

Annotations only cover the safety profile (readOnly, idempotent, openWorld, non-destructive); the description adds material behavior the annotations cannot convey: prices are cached airline fares in GBP, can change, may be flagged 'sample' as example-only data, and links are affiliate links via leavehacker.app/go with a disclosure obligation. These are exactly the disclosures an agent needs before quoting fares to a user.

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?

Core purpose and result shape are front-loaded, and the affiliate/staleness caveats earn their place. However, the middle is a run-on comma-spliced chain that could be split or tightened without losing content.

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?

For a 4-param read tool with an output schema, the description covers everything that matters: what is returned (one cheapest fare per destination, ordered), data freshness caveats, currency, and the affiliate link behavior the agent must disclose. Return-value detail is correctly left to the output schema.

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 origin/depart/return/limit are already fully documented with formats and examples. The description adds only result-shaping context (one per destination, cheapest first, GBP) rather than parameter meaning, so the baseline of 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?

States a specific verb and resource ('Find the cheapest return flights from a departure airport') and adds the result shape: one per destination, cheapest first, with booking links. That is enough for an agent to distinguish it from every sibling, none of which return fares.

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?

Gives a concrete trigger example ('Find cheap flights from Manchester that fit the May bank holiday weekend') and an explicit prerequisite: derive the break's dates with best_days_to_book first. It does not state any when-not condition (e.g. one-way or multi-city trips), so it falls short of full routing guidance.

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