web_fetch

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

With no annotations provided, the description fully carries the burden. It discloses that content is untrusted, wrapped in a random-nonce fence, and should be treated as data. It explains pagination behavior (lossless splitting, total_pages, has_more) and mentions the datamark option for prompt-injection resistance. No contradictions.

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 description is reasonably concise and front-loads the main action. It could be slightly more concise, but it earns its length by including important details about security and pagination.

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?

Given the existence of an output schema (not shown but implied), the description does not need to explain return values. It covers pagination, security, and usage sufficiently. The tool has moderate complexity and no annotations, but the description completes the picture.

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 description coverage is 100%, so baseline is 3. The description adds value by explaining pagination semantics (page, total_pages, has_more) and the purpose of tier and datamark, which are already described in schema but with additional context.

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 clearly states it fetches one URL, extracts clean Markdown, and returns one token-budget page. It distinguishes itself from siblings by mentioning use for pages from web_search or user-provided URLs, and references web_open for reading subsequent pages.

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?

Explicitly says when to use: 'Use this to read a page found via web_search, or any URL the user gives you.' It differentiates from web_open by noting that web_open is for reading the rest of the pages. While not providing extensive when-not guidance, the context is clear enough.

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