web_fetch

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

Annotations already supply readOnlyHint beyond which the description adds meaningful context: it returns 'raw Markdown from Jina Reader' and clarifies the tool is non-interactive (no login, click, form, or visual inspection). This disclosure exceeds the annotation and helps the agent calibrate expectations. A 4 reflects the extra value without being exhaustive.

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 fluff. The core purpose is front-loaded, followed by usage exclusions and a note on return format. Every sentence serves a purpose—no repetition or filler.

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 single-parameter read-only tool, the description completely covers what the agent needs: when to invoke it, what it returns, and what it is not for. No output schema is present, but the return type is disclosed. Nothing essential is missing.

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?

The sole parameter (url) is fully documented in the schema with a detailed description ('Exact HTTP(S) URL... pass source URLs unchanged'). Schema coverage is 100%, so the description does not need to add parameter info; the minimal restatement adds no extra meaning beyond the schema. Baseline 3 is appropriate.

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+resource: 'read, quote, summarize, or verify page text' from an exact HTTP(S) URL. It distinguishes itself from siblings web_search and x_search by clarifying it consumes their URLs, and differentiates from Browser/curl/shell by its non-interactive read-only role.

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 defines when to use (exact URL known, text-read task) and when not (URL discovery, need login/click/form/visual). Names alternatives (Browser, curl, shell) and states preference conditions. Provides clear routing guidance.

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