humanize_text

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

With no annotations, the description carries the full burden and does: it discloses the two execution modes (server-side vs. mode='delegated_to_caller'), the return fields (rewritten_text, instructions), the caller's obligation to apply instructions preserving facts/figures/names/dates/quotes/URLs, and that voice_sample governs style only. This is unusually complete 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-loaded with 'Optional' then the core action, and every sentence carries information. The detector-explanation sentence is slightly digressive but justifies the 'prefer review_draft' guidance, so it largely earns its place.

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?

No output schema and no annotations, yet the description covers modes, return values, constraints on fact preservation, and parameter behavior. An agent has everything needed to call and correctly handle this tool.

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 0%, so the description must compensate. It fully explains voice_sample (optional, matches writer rhythm, style only, never contributes facts) with a default-behavior note. The 'text' parameter is only implicitly documented via the delegated-mode reference to text_to_rewrite, so one gap remains.

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+resource ('Rewrite a draft to strip AI writing tells, keeping facts intact') and names the sibling it is not ('Prefer review_draft'). An agent can separate this from review_draft and score_ai_text without opening the schema.

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?

Explicitly gives when-not ('Prefer review_draft', 'Use this only to edit text the writer already wrote'), why-not (rewrites produce machine-written prose again), and a disclosure obligation ('tell them it was used'). This is a textbook routing instruction.

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