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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, and the description adds real substance on top: no charges, no cross-account enumeration, no automatic retries on the caller's behalf. It also discloses that anonymous receipt handles are secret capabilities that expire, which is a behavioral property not encoded in any annotation; only failure/expiry handling is left unstated.

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?

Two sentences with no filler; the recovery mechanism and its credential come first, and the negative guarantees follow in a compact list. The telegraphic fragment ('No charges, writes, cross-account enumeration, or automatic retries.') is dense but every item carries information.

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 3 parameters at full schema coverage and an output schema present, the description need only cover the credential model and side-effect profile, which it does. The remaining gap is sibling disambiguation against get_operation/get_operation_result and what happens when a key is expired or unknown.

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 meaning beyond the schema by explaining the conditional auth model: authenticated actions need the original idempotency_key while anonymous flows use a secret, expiring receipt handle. The expiry characteristic is the main piece of semantics not already present in the property descriptions.

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: 'Recover one action's durable operation using its original idempotency_key,' which tells an agent exactly what the call returns for a given action. However, it never distinguishes itself from the close siblings koskamo_get_operation and koskamo_get_operation_result, and the tool name (list_operations) points in a different direction than the actual single-operation recovery behavior.

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?

The recovery-after-response-loss scenario is implied by the title and the 'retain it across retries' framing, and the description draws the authenticated-vs-anonymous distinction for which credential to supply. It gives no explicit when-not-to-use guidance and never tells the agent why to pick this over get_operation or get_operation_result.

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