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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description still adds real context beyond that: no model involved, no fetching, no payment or automatic paid fallback, and an explicit 32768-byte input cap. It is candid that token savings are not guaranteed, which is honest behavioral disclosure.

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-loads the 'FREE, no key' hook well and stays reasonably short, but repeats the negative-fetching idea twice ('No model, fetching' and 'no fetch') and repeats the paid-fallback concept, wasting a sentence on redundancy.

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?

Output schema exists, so return values need not be described. Combined with annotations covering safety, the description supplies the remaining operational constraints (input size, offline, no cost) that an agent needs to call this correctly; only the per-parameter semantics remain thin.

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 carry parameter meaning, and it largely does not. It gestures at 'source' (sourceUrl) and 'truncation' (maxChars) and states the 32768-byte input limit, but never explains maxChars' default/max/floor of 256 or what sourceUrl is used for, leaving the agent to infer from the schema.

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 HTML) and names the output form: bounded readable blocks with source, truncation and size estimates. The phrase 'supplied HTML' implicitly distinguishes it from fetch-based siblings like web_page_pack_fetch, though it never names an alternative explicitly.

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?

Implies the usage context ('supplied data only; no fetch') so an agent understands this is for HTML it already holds, and 'FREE, no key' signals cost constraints. It stops short of naming when-not or the specific alternative tools to route to when data must be retrieved.

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