emulator_order_demo

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

The annotations already signal mutation (readOnlyHint=false), a closed environment (openWorldHint=false), and non-idempotency, and the description usefully adds that the run injects a controlled failure, performs a repair, and cleans up. That lifecycle detail is real value beyond the annotations. However, it leaves open whether cleanup is guaranteed on failure, whether it is safe to re-run, and what observable outcome distinguishes success.

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 front-loaded sentence with no filler; every clause (synthetic services, controlled failure, repair, cleanup) carries information about what the run does. Nothing is redundant with the title or 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?

With no parameters and no output schema, the description carries the full burden of explaining what the agent gets back and how the run terminates. It describes the phases but not the result (pass/fail report? artifact list?) nor guarantees about the environment afterwards. Adequate to decide whether to call it, but incomplete for interpreting the outcome.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description's job is only to convey the run mode, which it does implicitly through the failure/repair/cleanup sequencing.

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?

The description names a concrete verb ('Run') and a concrete subject: a synthetic S3 + DynamoDB + SQS order workflow that deliberately fails, repairs, and cleans up. That is clearly distinct from the sibling tools, which each act on a single primitive (s3_put_object, sqs_send_message, etc.). It stops short of stating that this is an end-to-end demo/verification scenario, but the intent is unambiguous.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no named alternative such as emulator_self_test or emulator_health. Usage is only implied: an agent must infer that this is an end-to-end walkthrough rather than a general-purpose operation. Nothing tells the agent what preconditions (e.g. emulator_start) must hold first.

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