Probe Page

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

The description adds substantial behavioral context far beyond the annotations: localhost auto-tunneling with fast-fail pre-flight probe, batch-mode session/timeout sharing, the content-settle readiness semantics ('DOM going quiet' rather than network idle or load), and partial-failure behavior where a single failed target's error appears in result.error without failing the whole batch. The readOnlyHint and openWorldHint annotations are consistent with this read-only probing tool, and there is no contradiction.

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 text is lengthy but deliberately sectioned with labeled headers (WHEN/WONT NOT use, LOCALHOST SUPPORT, BATCH MODE, READINESS), so an agent can scan or read with minimal overhead. Every sentence carries a distinct functional fact; a few points (e.g., the full waitForLoadState/networkidle discussion) could be tightened but are not 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?

There is no output schema, so the description must carry the return contract - and it does: it lists screenshot, title/finalUrl/statusCode/loadTimeMs, structured console errors, per-URL network summary, and the includeHtml option. Batch limits, localhost handling, timeouts, wait options, and error semantics are all covered; nothing an agent needs to call the tool correctly is missing.

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?

Since schema description coverage is already 100%, the baseline is 3 and the schema does the heavy lifting. The description adds genuine decision-making beyond that baseline: waitForSelector nuance for SPA mounts, the explanation that networkidle is accepted but never issued against live sites, and batch-mode guidance that up to 20 targets share one execution unit for speed.

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 opens with a specific verb and resource - 'Probe one or more URLs and return their rendered state' - and enumerates the exact return payload (screenshot, title/finalUrl/statusCode/loadTimeMs, console errors, per-URL network summary). It also distinguishes itself from its sibling by naming check_app_in_browser explicitly in the NOT FOR section.

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 WHEN TO USE section gives concrete agent-facing queries ('did I just break /settings?', 'smoke-test these 5 routes') and the decision constraints (fast, no LLM cost, no agent loop). The NOT FOR section explicitly rules out scenario verification and interaction and names the alternative: 'Use check_app_in_browser for those.' An agent knows exactly when to pick this tool over its sibling.

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