Clean and normalize text

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral context beyond this: it states the tool is fully offline, makes no network request, and clarifies that removeUrls strips every URL indiscriminately because the server cannot distinguish live from dead links. This gives agents an accurate mental model of side effects and limitations.

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?

The description is two sentences long, front-loaded with the tool's core operations, and has no filler. The privacy/offline statement earns its place as an important behavioral constraint. Every clause contributes either operational scope or a safety guarantee.

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?

The definition is complete for the tool's complexity: all four parameters are documented in the schema, an output schema exists, and annotations cover read-only, idempotent, and non-destructive behavior. The description adds the offline guarantee and optional transformations. No critical behavioral or usage gap remains for an agent to select and invoke this tool correctly.

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?

The input schema covers all parameters with descriptions, and the context signal reports 100% schema description coverage, so the baseline is 3. The description adds value by summarizing the parameter effects in behavior-oriented terms (e.g., 'collapse repeated spaces,' 'convert smart punctuation to ASCII,' 'remove URLs') and noting which transformations are default versus optional. This helps an agent anticipate the tool's default behavior without opening 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?

The description opens with 'Normalize messy text' and enumerates specific operations: collapsing repeated spaces, stripping invisible characters, unifying line endings, and optional transformations. This clearly distinguishes clean_text from its PDF-related siblings (pdf_info, merge_pdfs, extract_pdf_pages), which operate on binary documents rather than raw text.

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 clearly implies when to use the tool: whenever raw, messy text needs normalization before further processing. It also adds a relevant constraint by emphasizing the tool runs entirely offline, which is useful context for privacy-sensitive data. However, it does not explicitly state when not to use it or name alternative text-processing tools, though none are provided among the siblings.

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