url_to_markdown

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

With no annotations, the description carries the full burden. It usefully discloses JS execution, the Markdown output shape, and the $0.01 cost, but says nothing about failure modes, timeouts, size limits, or how JS-heavy/blocked pages behave.

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?

One tightly packed sentence that front-loads the mechanism and output format, then adds purpose and price. 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?

No output schema and no annotations, and an 8-parameter surface with only half documented. The description covers what an agent needs to know about the result and cost, but leaves parameter behavior and error conditions partly unaddressed.

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?

Only 50% of the 8 parameters are described in the schema; wait_until, output_path, idempotency_key and url carry no documentation there. The description adds nothing about timing controls or output destinations, and its 'return it as Markdown' phrasing sits awkwardly against the default output=json mode.

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 (fetch), resource (public web page), mechanism (real browser with JavaScript) and output (GitHub-flavoured Markdown with absolute links and tables). This is far more precise than the sibling pdf/render/screenshot tools and an agent can tell what it produces without opening the schema.

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?

Names concrete use cases (reading, summarising, archiving pages as text) and scopes the tool to 'public' pages, which implicitly rules out authenticated content. It never names an alternative sibling (e.g. screenshot for visual fidelity, render for full-page capture), so routing is inferred rather than stated.

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