Generate multi-model test variants

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

Annotations already declare readOnlyHint=true; the description reinforces this as 'Read-only' and adds behavioral detail about the return format (prompt, path, instruction) and manual execution requirement. No contradictions.

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 four sentences with all essential information front-loaded. No redundant text; every sentence serves a purpose.

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?

No output schema exists, but the description adequately covers the return format (prompt, storage path, instruction) and the intended workflow. It leverages sibling context and annotations. Minor gap: does not explain the 'instruction' field.

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 80%, so baseline is 3. The description adds value by explaining the default model tiers and how they surface different failure concepts, which is not in the schema descriptions.

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 clearly states the tool fans a generation prompt across model tiers (fable, opus, sonnet) and returns per-tier prompts and storage paths. It distinguishes itself from siblings (suggest_test_stub, generate_test) by mentioning it builds on them and by requiring submission to save_generated_test.

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?

The description specifies usage for a bug/ticket and provides explicit workflow: run each tier yourself then submit to save_generated_test. It references sibling tools but lacks detailed exclusion criteria for when to use this vs alternatives.

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