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

Annotations already cover readOnly/idempotent/non-destructive, but the description goes further: rate-limit consumption without test credits, 404 on unknown/pruned/foreign batchId, account-lifetime retention with no pruning, and deduplication so counts sum to totalUrls. These are non-obvious behaviors an agent needs.

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?

Front-loads purpose, then polling loop, then routing, then edge-case behaviors. Every sentence contributes distinct, actionable information with no filler.

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?

Output schema exists, so return values need no explanation. For an async batch-polling tool the description still covers the full lifecycle: polling termination, follow-up routing, retention, error handling, and counting semantics.

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 batchId param is fully documented there, so the description's restatement that it comes from gvt_run_visibility_batch adds little. Baseline 3 is appropriate when the schema carries the parameter semantics.

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 (retrieves) and resource (visibility testing batch) plus the exact payload (progress, state, tids). It is clearly distinguished from sibling readers like gvt_get_batch_summary and gvt_get_test_results, which it explicitly routes to.

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 an explicit polling loop: call with the batchId from gvt_run_visibility_batch until status is completed or failed. It also names the follow-up tools and the condition (tid present after a test completes) that selects each, leaving nothing to inference.

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