Save generated test variants

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

The description adds valuable detail beyond annotations: explicit deduping logic (whitespace normalization, duplicate dropping), output file naming convention, and reiteration of read-only behavior. This helps the agent understand side effects and output structure.

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?

Two sentences: first covers the core process and deduping, second highlights read-only nature and output. Efficient and front-loaded, with no extraneous information. A brief example output path would improve clarity.

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?

Covers main inputs, processing (deduping), and outputs (file names). Lacks error handling, prerequisites (e.g., ticket existence), or volume limits. For a tool with no output schema, the description provides sufficient context for basic usage.

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 coverage is low (33%), but the description explains the ticket parameter's role in file naming and the variants parameter's composition (model+content). The project parameter lacks explanation. The description partially compensates for the low coverage but leaves project unclear.

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 explains the tool ingests test variants, dedupes, and returns file contents for writing. The verb 'Ingest... returns' clarifies it does not actually save to disk, distinguishing it from sibling save tools. However, the title 'Save generated test variants' may mislead an agent into thinking it writes files directly.

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?

No guidance on when to use this tool vs alternatives like generate_test or generate_multi_model_tests. The description assumes the agent already knows it should call this after generating variants, but does not specify prerequisites or contrasting scenarios.

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