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

Annotations cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds operational detail annotations cannot express: 256 KB cap, 6-second timeout, 10 calls/minute rate limit, SSRF blocking of private networks, and an explicit untrusted-data warning. This is exactly the value-add layer descriptions should provide.

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?

Four tight sentences in a deliberate order: purpose, use case, hard limits, security caveat. Nothing is repeated from structured fields and no sentence is 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?

With no output schema, the description carries the return-value burden and does so by listing the fields returned. Combined with the rate limit, timeout, size cap, and untrusted-data guidance, an agent has everything needed to call this correctly.

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 100% schema coverage the baseline is 3, but the description goes further by constraining the valid value domain – the URL must resolve to a public http(s) address, private networks are blocked. That restriction is not encoded in the schema and materially affects how an agent forms the argument.

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 ('Fetches one public web page') and enumerates the exact return payload (title, description, OG/Twitter tags, canonical URL, icon), so an agent knows precisely what it gets without opening the schema. It is clearly distinguishable from generic siblings like anansi_free_data or text_tools.

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?

'Use it to preview or label a link' gives explicit usage context, and the public-address-only limit implicitly states the when-not case. It doesn't name an alternative sibling for related tasks (e.g. fetching body text), but no obvious sibling overlap exists.

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