ASO Run

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

Annotations already declare the mutation/safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the description only needs to add context. It usefully notes the side effect of creating an outputs skeleton and that skill instructions are returned, but it does not say what happens to pre-existing outputs on a re-run, despite claiming idempotency.

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?

Three short, front-loaded sentences with the action, trigger, and follow-up in priority order. The trailing 'Returns: {ok, outputs_dir, instructions}' is mild redundancy given a declared output schema, but it is compact.

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 annotations, a 100%-covered schema, and an output schema, the description only needs to supply purpose and sequencing, which it does. The main missing piece is disambiguation from aso_scaffold_outputs and behavior on repeat invocation.

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 100% and the single app_dir parameter is fully documented in the schema, so the description adds nothing beyond it. Baseline 3 is appropriate when the schema carries all parameter meaning.

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: 'Start the mandatory ASO stage: create the outputs skeleton and return the skill instructions.' An agent can tell this is the ASO stage entry point rather than a completion or validation step. It does not, however, distinguish itself from the closely named sibling aso_scaffold_outputs, which the phrase 'create the outputs skeleton' would otherwise suggest.

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?

Gives explicit activation context ('Use when: the pipeline reaches ASO') and names the terminating counterpart ('Finish with aso_complete'), which is genuine routing information. It stops short of exclusions, e.g. when to prefer aso_scaffold_outputs over this tool or what to do if the stage was already started.

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