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

Annotations only declare the generic mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description earns credit for disclosing two real behaviours: the operation is simulated first, and it produces both an outbound written claim from the support mailbox and a follow-up task. It does not state what happens on the simulated pass or whether a second call is needed to commit.

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?

A single dense sentence plus a short applicability note, front-loaded with the action and its purpose. Nothing is padded, though the bracketed '[Support desk]' prefix and trailing 'Works on:' fragment are slightly redundant.

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 not be described, and annotations cover the safety profile. However, for an 11-parameter mutation with near-zero schema coverage, the description leaves an agent unable to populate the financial and attachment fields correctly or know whether a confirmation call follows the simulation.

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 only 9% (just 'account'), so the description must carry the load for 11 parameters. It only maps loosely onto the `type` enum via the claim-type list; awb, attachments, declared_value, amount_expected, amount_collected, courier_account, thread_id and order_ref are entirely unexplained, including which are required for which claim type.

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?

A specific verb ('Propose opening a claim') plus the target ('at the courier') and an enumeration of the qualifying claim types (lost, damaged, wrong COD, not delivered). It distinguishes this from adjacent siblings such as warranty_case_open and returns_create_awb by naming the courier-claim domain, though it never explicitly states the boundary against those 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?

'Simulated first' and 'Works on: Support desk' imply the context in which it is valid, but no alternative tool is named and no when-not conditions are given. An agent must infer that this is the safe dry-run path before some other confirm step.

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