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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the bar is lower. The description adds genuinely useful behavioral context beyond them: no fetch, no generated summary, no payment or automatic paid fallback, and a hard 32768-byte input ceiling with a bounded text budget.

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?

Key constraints are front-loaded in the opening sentence, but the 'no fetching / supplied data only / no fetch' prohibition is stated three times across separate sentences, which is redundant padding rather than earned content.

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 an output schema present, return values need no explanation, and annotations cover the safety profile. The description is nearly complete, lacking only per-parameter semantics for 'section' and 'sourceUrl' and any positive usage cue.

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 description coverage is 0%, so the description must compensate. It loosely covers two of four params ('bounded text budget' ~ maxChars, '32768 UTF-8 bytes' ~ html maxLength) but says nothing about 'section' selection or what 'sourceUrl' is for or whether it is validated against the supplied HTML.

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 ('Pack') and resource ('supplied Wikipedia article HTML') plus the outputs it produces: sections, source links, attribution, and a bounded text budget. The word 'supplied' plus 'No fetching' implicitly separates it from fetching siblings like web_wikipedia_read/web_wikipedia_pack, though it never names them.

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?

Gives a clear negative condition ('No fetching or generated summary', 'Supplied data only'), which implies the tool is for when you already have HTML in hand. But it never states the positive when-to-use case or explicitly names an alternative for agents that don't yet have the HTML.

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