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

Even with idempotentHint=true already present, the description adds the exact idempotency contract: same credential actor and exact content reuse returns the original receipt, while changed actor/content conflicts. It also discloses immutability, authentication derivation, and the never-fetch policy for locator strings, which are not visible in annotations.

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 with no filler: first sentence states purpose, second scope, third evidence security, fourth idempotency. Each clause carries distinct decision-relevant information and the most important facts are front-loaded.

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?

The definition covers purpose, prerequisite, auth model, security boundary, and idempotency contract, which is substantial for a finalization operation. It stops short of describing the receipt/response shape or the intended format of several parameters, but those are secondary to safe invocation given property names and types.

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?

The description adds real meaning for evidence (bounded opaque objects; locator-looking strings are never opened or fetched) and for idempotency_key (same-key retries vs conflicts). However, schema description coverage is 0% and most required parameters (runner, environment, source_revision, verdict, summary, scenario identifiers) are left to their property names without further explanation.

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?

Opens with a specific verb ('Finalize') and a precise resource ('one immutable validation run for an exact owned ticket scenario revision'), so the operation is immediately distinguishable from ticket_create, ticket_update, and ticket_scenario_revise. The 'exact owned' qualifier also signals the scenario-version/hash binding that shapes the call.

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 scope prerequisite ('Requires the opt-in tickets:validate scope') and retry/conflict semantics tell the agent the conditions under which calling is valid and what happens on repeats. It does not explicitly name an alternative tool or list when not to use it, but the domain context makes the intended use clear.

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