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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower, and the description still adds real behavior: it returns source timestamps, hashes, field provenance, conflicts, and a diff against a prior snapshot, and it discloses the free-preview limitation and that no browser rendering or background monitoring occurs. It does not mention rate limits or failure modes on unsupported URLs.

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 tight sentences with no filler; the core action is front-loaded and the return payload and scope limits follow. Slightly dense with jargon (field provenance, hashes) but each clause earns its place.

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 correctly carries the return-value burden by enumerating timestamps, hashes, provenance, conflicts, and change deltas. Combined with the source restriction and preview limitation, an agent has enough to invoke it, though supported-URL failure behavior and preview limits (record caps) remain unspecified.

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 50%: the url parameter has no description in the schema, but the description compensates by constraining it to "supported Allbirds and tentree product URLs." It also clarifies that "previous" is a caller-supplied prior snapshot and that comparison is against the identical URL, adding meaning beyond the schema's brief note.

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 (Retrieve) plus resource (public product metadata and variant details), scoped to named sources (Allbirds, tentree product URLs). An agent can tell this is a product-page extraction tool rather than a generic HTML scraper, though no sibling is named explicitly to sharpen the boundary against penny_html_extract or penny_catalog_audit.

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?

"Narrow free preview; no browser rendering, purchases or background monitoring" sets scope and exclusions, giving implied guidance about when this applies (static product metadata fetch). However, no alternative tool is named and there is no explicit when-to-use-vs-when-not routing statement.

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