willow_web_fetch

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

Annotations only provide readOnlyHint=true, but the description goes far beyond that: it discloses the external-guard interception, private/loopback blocking with actual name resolution rather than mere matching, per-redirect re-checking, and the `redirects` output chain. It also surfaces permission/lease requirements, offering substantial behavioral context not available in structured data.

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 compact yet dense, with every sentence contributing: purpose, behavior, security guarantees, sibling guidance, and prerequisites. It is front-loaded with the primary action and avoids fluff or repetition of schema details.

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?

Despite having no output schema, the description covers the tool's essential contexts: safe URL constraints, redirect handling, what is returned (text plus redirect chain), and required entitlements. It also links to the natural preceding action (willow_web_search). Given the tool's security-sensitive nature, this is a thorough and self-sufficient description.

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?

With 0% schema description coverage, the description must compensate, and it does for key params: 'wrap' is explained via 'sandwich defense when wrap=True', and 'url' gains meaning through the public-destination constraint. However, 'max_bytes' and 'app_id' are left unexplained, leaving partial gaps. Still, the description provides meaningful semantics beyond the bare schema names.

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 identifies a specific verb+resource: 'Fetch a URL through external-guard (not native WebFetch).' It distinguishes itself from other tools by explicitly contrasting with native WebFetch and directing users to willow_web_search for URL discovery, making the tool's unique role unambiguous.

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?

The description gives concrete contextual guidance: use willow_web_search to discover URLs first, and notes the operational prerequisites (web_net + consent.internet + egress lease). It also explains the safety filtering behavior, which helps users know what URLs are acceptable. It does not explicitly state when NOT to use this tool versus alternatives like willow_institutional_search, so it misses full exclusionary clarity.

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