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

No annotations exist, so the description carries the full burden and does: it discloses the 0.10 USDC cost, that the result is a ticket rather than an instant refund, that a human operator decides eligibility and airline penalties off-band, and that refunds are all-or-nothing. That is exactly the kind of non-obvious behavioral context an agent needs before spending money.

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?

Four sentences, front-loaded with the core action and cost, then the critical caveat, then the exclusion, then the inputs. No sentence is redundant and none repeats 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?

An output schema exists so return values need no explanation, and annotations are absent but the description compensates with cost, latency/process semantics, prerequisites, and failure context. Nothing an agent needs to decide whether and how to call this 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, but the description adds cross-tool provenance the schema cannot: support_code must come from travel_create_booking_intent and family_name must be the lead passenger's from travel_book_flight. It adds meaning for two of five parameters without restating types or limits.

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+resource (file a manual refund request) and narrows it to booked intents with escrow already captured. It distinguishes itself from the automatic path taken for active intents, so an agent can separate this tool from travel_get_booking_intent and the booking worker's behavior without opening a 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?

Explicit when-to-use (status=booked, escrow captured), explicit when-NOT (active intents are refunded automatically to refund_wallet, do not call this), and names the sibling tools that supply the required credentials. Prerequisites are spelled out via the support_code and family_name provenance.

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