atcCheck

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description adds value by explaining the execution flow (variant, worklist, run, readback) and the risk of misuse (500 error). It also describes output ordering ('findings are ordered by priority, 1 being the worst'), which is behavioral context beyond the safety 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?

The description is moderately long but every sentence carries necessary information. It front-loads the core purpose, clarifies the internal workflow, and includes a practical warning. No redundancy or filler; it earns its length.

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?

Given 9 parameters and no output schema, the description covers key aspects: what the tool does, the expected output content, ordering, severity semantics, and a known failure mode. It does not detail exact return structure (no schema exists), but it provides enough for an agent to invoke correctly. The only minor gap is absence of explicit mention of authentication or rate limits, which are not indicated in annotations either.

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%, so baseline is 3. The description adds meaningful context: explains the variant default ('Defaults to the system check variant from atcCustomizing'), the cap semantics ('maxResults' and 'maxFindings' with counts always for everything found), minPriority severity ordering, and the escape-hatch purpose of objectUrl. This enhances understanding beyond the schema.

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 ('Run the ATC checks') with explicit scope ('over an object or a whole package') and detailed description of the output (findings with priority, check, message, source line). Clearly distinguishes itself from sibling tools by positioning as the whole sequence in one call, not requiring separate steps like variant selection or worklist creation.

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?

Provides clear context on when to use the tool ('the whole sequence in one call') and warns about a specific pitfall ('getting it wrong is what made a run answer 500 (the run needs a worklist id where the library asks for a variant)'). It implicitly differentiates from component tools but does not explicitly name alternatives or state when not to use, hence not a 5.

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