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

Annotations declare readOnlyHint=true and openWorldHint=false, so safety is covered, but the description frames every operation as if it always happens, while the schema shows most (stripHtml, removeUrls, removeEmoji, removeEmails, case) are opt-in and default false. That framing risks an agent calling with only `text` and expecting HTML to be stripped when it will not be. Nothing is said about maxLength truncation behavior either.

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?

A single tight sentence with the primary operation (HTML stripping) front-loaded and no filler. The compressed list format is efficient, though it is precisely the compression that blurs the opt-in nature of each item.

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?

For a tool with a nested 11-option object, zero schema descriptions, and no output schema, the description should say which transforms run by default and what maxLength does. Neither is present, so an agent cannot predict the output of a minimal call with confidence.

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% and there is a nested options object with 11 sub-properties, so the description carries real weight. It names most operation categories (stripHtml, decodeEntities, unicode, whitespace, asciiPunctuation, removeEmoji, removeUrls, removeEmails, case) but omits maxLength and removeControlChars entirely and never states which flags default on versus off, so it only partially compensates.

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?

Enumerates concrete text-transformation operations (HTML stripping, entity decoding, Unicode/whitespace/punctuation normalization, emoji/URL/email removal, case change), which clearly identifies the resource and the verbs applied to it. It is distinguishable from clean_csv by the 'text' framing, though no sibling is named 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?

The description contains no guidance on when to reach for clean_text versus page_extract, page_to_markdown, or clean_csv, and no preconditions are stated. An agent must infer its place in the pipeline from the name alone.

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