emulator_self_test

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

The annotations declare readOnlyHint=false, destructiveHint=false and idempotentHint=false; the phrase "with cleanup" usefully explains why a mutating test leaves no residue and is not destructive. However, it says nothing about duration, what output indicates success/failure, or whether it can be run concurrently, so the added context is real but partial.

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?

One short, front-loaded sentence with no filler; the verb and the three services come first and "with cleanup" is appended as a qualifier. Appropriately sized for a zero-parameter tool.

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?

For a no-parameter, no-output-schema utility, the description covers what it does and the cleanup guarantee, which is most of what an agent needs. It is slightly incomplete in not describing the result shape (e.g., per-service pass/fail), which matters more since no output schema exists.

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 no parameters, which puts the baseline at 4, but with an empty schema there is simply no parameter meaning for the description to add. The single sentence also does not explain what the call returns, which is the only semantic gap available here.

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 ("Run") and resource ("isolated local S3, DynamoDB, and SQS round trips"), so an agent knows this exercises all three emulated services end to end. It stops short of differentiating itself from siblings like emulator_health or emulator_doctor, which is the only thing keeping it from a 5.

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?

"Self test" implies a verification/diagnostic use case, and "isolated" hints at a safe context, but the description never says when to prefer this over emulator_health or emulator_doctor, nor any prerequisites such as services needing to be started.

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