Humanize a document

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

With no annotations, the description fully carries the burden and does so exceptionally. It discloses cost (100 credits per 1000 words), the iterative behavior with re-runs, that only flagged passages are touched when a report is provided, output saving next to the source, and the returned path. This is far beyond the bare minimum and gives agents clear expectations.

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 about four sentences long, starts with the core purpose, and every sentence adds a distinct piece of information: main functionality, optional report usage, iterative re-run guidance, and cost warning. There is no redundant or filler text.

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?

Despite 9 parameters and no output schema, the description covers all essential context: main use case, optional report integration, re-run strategy, file type constraints, output path behavior, and cost. Combined with the fully described schema, this gives an agent everything needed to invoke the 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?

Schema coverage is 100%, so parameters are well-documented, but the description adds contextual meaning beyond schema by explaining the strategy choice (balanced vs aggressive) for first and second passes, the purpose of report_path, and the default output behavior. It also ties the re-run guidance to the strategy and report parameters, helping agents make informed choices.

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 clearly states the tool rewrites .docx or .pptx files to read as human-written and lower AI detection scores, while preserving meaning, citations, tables, and layout. This specific verb+resource scope distinguishes it from sibling tools like condense_document or translate_document.

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?

It explains when to use the tool, including the option to pass a Turnitin/iThenticate report to rewrite only flagged passages, and advises re-running with balanced strategy if a fresh report still flags results. It does not explicitly contrast with alternatives, but the guidance implies the primary use case and iterative workflow.

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