fetch

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), so the bar is lower; the description still adds real behavioral context — cursors serve the same saved snapshot without a new API call, and they can expire or be evicted. It does not cover error responses or rate limits, which keeps it from a 5.

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 sentences, zero filler, with the primary capability front-loaded before the mutual-exclusion rule and cursor caveats. Every sentence carries distinct information.

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?

Covers both invocation modes, the parameter constraint, and cursor lifetime, and an output schema exists so return values need not be described. The main remaining gap is not stating what happens on an expired/evicted cursor or an unreadable URL.

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 a cross-parameter constraint the schema cannot express: exactly one of url or cursor must be supplied. It also clarifies that cursor values come from next_cursor in prior search or fetch results.

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 ('Read a web page as Markdown') plus a second mode ('continue a cached page'), and names the sibling tool 'search' as a cursor source. An agent can distinguish this from search without opening either 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?

Gives an explicit selection rule ('Supply exactly one of url or cursor') and explains the trade-off: cursors avoid another API request but can expire or be evicted. It stops short of naming an alternative path when a cursor is invalid, but the routing context is clear.

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