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

Goes beyond annotations by disclosing that execution is asynchronous and that plan limits apply, plus retry/idempotency behavior. It omits where results land (webhook versus polling via get_bulk_capture) despite the schema exposing webhookUrl, which leaves a meaningful behavioral gap.

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 tightly packed sentences, each contributing a distinct fact (batching limit, async nature, quota caveat, retry key). No filler or restatement 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?

For an asynchronous batch job with no output schema, an agent needs to know how completion is signaled. The description never connects to get_bulk_capture, list_bulk_captures, or webhook delivery, and the webhook parameters are left unexplained.

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 0%, so the description must carry the burden, and it only names urls, per-URL options, and idempotencyKey. The webhookUrl and webhookSecret parameters are undocumented in both schema and description, and the large nested defaults/actions/outputs structures get no explanatory prose.

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 (submit), resource (screenshots), and distinguishing scope (up to 100, asynchronously, bulk URLs/options). It implicitly separates the tool from capture_screenshot by emphasizing bulk, but never names the sibling or clarifies the boundary explicitly.

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?

"Submit up to 100 screenshots asynchronously" and "Reuse idempotencyKey on retries" give real operational context, but there is no explicit guidance on when to choose this over capture_screenshot or a schedule, and no mention of how to retrieve results afterward.

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