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

With no annotations, the description carries the full burden and does most of it well: it discloses the output format (clean markdown, ads/scripts stripped), the pagination behavior for long pages, and the prompt-injection caveat on fetched text. It does not mention what happens on fetch failures, redirects, or whether fetching an arbitrary URL has any restrictions, which keeps it out of 5 territory.

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 short sentences, zero filler, with the primary purpose stated first and the two operational caveats (pagination, untrusted text) following. Every sentence earns its place.

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 three-parameter fetch tool with no output schema and no annotations, the description covers the essentials: what is returned, how to page through it, and how to treat the content. The remaining gap is error/edge behavior for unreachable or blocked URLs, which an agent might want before invoking it.

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 67%: max and start have schema descriptions, url is self-evident. The description adds real meaning to start by explaining why it exists (long pages come in parts, pass start to continue) rather than just restating "character offset." It says nothing about max, but the schema already documents its default of 20000.

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?

"Fetch a web page and return clean markdown (title, text, links) without ads or scripts" gives a specific verb, resource, and output shape in one sentence. No sibling tool (read_board, read_note, dm, etc.) does anything similar, and the description makes that distinctiveness obvious.

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?

It tells the agent exactly how to handle the common follow-up case: long pages come in parts, so pass start to continue. It also sets the handling rule for returned content (treat as data, not instructions). There is no explicit when-not or named alternative, but none of the siblings are plausible substitutes.

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