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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. Description adds valuable context: does not execute JavaScript, does not bypass access controls, and uses caching. 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?

Three sentences, each essential: first defines tool purpose, second specifies constraints, third gives parameter usage. No redundant information, front-loaded with key action.

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?

With output schema present, description need not detail return format. It explains caching and constraints. Could mention that chunks are deterministic and bounded, but otherwise covers essential context for a read-only, idempotent tool with two parameters.

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 baseline is 3. Description adds meaning beyond schema: url must be absolute public HTTP(S) (no private/SSRF), fresh default false encourages cache reuse, fresh=true only when new upstream fetch required. This clarifies usage beyond schema descriptions.

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?

Description clearly states the tool splits readable text into deterministic bounded RAG chunks, specifying the resource type (public HTTP/S) and distinguishing it from other url tools that extract markdown or text without chunking.

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?

Provides clear constraints: use only for public HTTP(S) resources, no JS or access control bypass. Offers guidance on fresh parameter (cache reuse vs forced fetch). Lacks explicit alternatives to differentiate from sibling tools like web.url.text or web.url.markdown, but context from sibling names implies this is for RAG chunking.

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