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

Goes well beyond the annotations by disclosing quota accounting per capture, cache-hit conditions via ttl, the 30000-character truncation of returned content, and that the screenshot link requires the caller's own access key. It also flags the prompt-injection risk of third-party page text, which is exactly the kind of safety context annotations cannot express.

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 dense sentences, front-loaded with what is captured and returned before cost and safety caveats. The trailing raw endpoint string ('GET /urltoimage?response_type=json&extract_text=true') is redundant noise that a tool caller cannot use directly.

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 no output schema, the description carries return-value burden and does: text or HTML truncated at 30000 characters plus a screenshot cache link with an access-key caveat. Quota, caching, timeout-adjacent waiting, and untrusted-content handling are all covered for a 9-parameter tool.

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 100%, so the baseline is 3, but the description adds cross-parameter behavior the schema cannot: the interaction between ttl, fresh and quota cost, plus the text-default and 30000-char cap on the content parameter.

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 and resource ('Capture a public web page ... return its extracted text (default) or HTML') and names the exact payload shapes, which separates it cleanly from apiflash_capture_screenshot. The output modalities (text/HTML plus a screenshot cache link) are explicit.

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 clear context for when a fresh capture is worth it (ttl-cached repeats are free, fresh=true always costs) and warns that the page content is untrusted. It never explicitly states the alternative sibling to use when an actual image is wanted, so routing versus apiflash_capture_screenshot is left to inference.

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