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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), yet the description adds genuinely new behavior: Obscura renders first and ungoogled-chromium escalates for JS-heavy pages and bot walls, a 30 s render budget is enforced, and timeouts/5xx/unreachable hosts are skipped for 30 days with an error prefixed "FLAGGED until <ISO date>". The only shortfall is the vague throttling language ("a few fetches at a time") with no concrete limit.

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 capabilities and pitfalls (engine choice, keyless, throttling, budget, 30-day flagging with error format) are front-loaded in a single dense paragraph with no filler or marketing fluff. It drifts into telegraphic fragments ("Keyless; a few fetches at a time") that cost some readability, and the URL provenance line is expendable.

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 a no-output-schema fetch tool, the description covers the essentials an agent needs to call it correctly: output formats, engine selection, size/timeout controls, throttling, and the exact failure signature to expect. Remaining gaps are secondary, such as redirect or auth-walled page behavior and whether truncation by max_chars is signaled in the response.

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 baseline is 3, but the description earns a bump by explaining the escalation chain that gives meaning to engine=auto, which the schema only labels "Default auto." It also frames timeout_s as a total budget shared across both engines, reinforcing rather than repeating the schema text.

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 ("Fetch a public web page") and enumerates the four output shapes (markdown, text, links, html), which is far beyond a restatement of the name. It distinguishes itself from the separate obscura engine endpoint implicitly by explaining that this tool wraps both engines and can pin one via engine=obscura|chromium, though it never names tronbrowser_screenshot_page or obscura_fetch_page as alternatives.

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?

Guidance is present but operational rather than selection-oriented: it explains that auto is the default and that engine=obscura|chromium pins one, plus that the service is keyless and handles "a few fetches at a time." There is no explicit statement of when to use this versus the screenshot or obscura siblings, so an agent must infer routing.

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