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

Beyond the annotations (readOnly/idempotent/openWorld), the description discloses metering and cost (shared 100 calls/day per IP free bucket, then 1 credit per call over x402) and the caching signal in the response. That is genuinely actionable context an agent cannot get from the annotations.

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?

Front-loaded with purpose, then use/avoid, then returns, then metering — a sensible ordering. The dense return-shape string is somewhat heavy for a description, though it earns its place given no output schema exists.

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 enumerates the response shape (ok, url, title, meta subfields, jsonld, tables with caption/headers/rows, links, cached, took_ms) and covers cost. An agent has everything needed to call and interpret the result.

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 url and include_links are already documented. The description adds nothing about parameter semantics; the only hint ('links?') merely mirrors the include_links option in the return shape. Baseline 3 applies.

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?

Specific verb and resource ('Extract structured data from one public page') followed by an enumeration of exactly what is extracted (tables, JSON-LD, OG/Twitter/canonical/lang metadata). It is clearly distinguishable from web_fetch, web_metadata, and web_extract_schema by the stated payloads.

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?

Explicit 'When to use' (page has tables or schema.org JSON-LD needed as data, without an LLM) and explicit 'Do not use' routing to web_fetch for text and web_screenshot for images. Alternatives are named with the selecting condition.

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