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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld, non-idempotent), so the bar is lower; the description still adds the parallel-execution trait and the BYOK auth requirement (one key per model), which is the main operational gotcha. It does not mention cost/latency implications of fanning out across up to six external providers, nor what happens when a model errors mid-batch.

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 sentences, front-loaded with the action and the parallelism trait, then the return shape, then the auth prerequisite. No filler or repetition of the tool name.

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 an output schema present, the description needn't enumerate return fields, and it still names the headline results (PASS/FAIL, pass rates, latency, comparison table). Given a nested 8-parameter batch tool with BYOK auth, the main gap is failure/partial-success semantics and any batch-size or cost constraints.

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 only 50% across 8 parameters, and the description clarifies only the key mapping ('one key per model') and the shared image/test-case inputs, both of which the schema already conveys. It adds no meaning for threshold, system_prompt, image_mime_type, or the assertion_type/assertion_value pairing.

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 (compare) and resource (vision models on the same image and test cases), and explicitly scopes it against the sibling run_vlm_test_suite by saying it uses the same assertions but runs models in parallel. An agent can distinguish this from compare_models/compare_responses without opening any schema.

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 parenthetical '(same assertions as run_vlm_test_suite)' implicitly routes single-model runs to that sibling, and 'BYOK: one key per model' states the prerequisite for calling this. There is no explicit 'do not use when' clause or cost/rate-limit warning, so it stops short of a 5.

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