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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, etc.), the description discloses that it uses only buyer-supplied information, performs no external research, returns a draft for human review, and requires explicit wallet authorization for payment. These are valuable behavioral facts not present in the schema or annotations. There is no contradiction with the annotations – 'no outbound actions' is compatible with openWorldHint if that refers to model knowledge rather than live calls.

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 three to four sentences, with the primary purpose in the first sentence and essential operational constraints (payment, no external research, draft for review) following directly. It is front-loaded and every sentence contributes new information; no filler words. This is an exemplary concise structure.

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 five parameters, a nested input object, no output schema, and annotations that are only partially informative, the description covers the critical operational context well (payment authorization, no research, draft return). However, it leaves the parameter semantics unexplained, and with no output schema the agent must infer the exact output format. The description is adequate but not fully complete: it misses mapping between supplied text and schema fields.

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%, yet the description mentions none of the five parameters by name or purpose. 'Supplied text' gives only a vague sense that text is the input, but does not clarify whether it maps to `brief` or `source_text`, nor explain `audience`, `result_expires`, `idempotency_key`, `result_signature`, or `payment_signature`. With the schema offering zero descriptions, the tool description fails to compensate, leaving an agent guessing about parameter roles.

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 'Rewrite supplied text in plain language and explain unavoidable technical terms without adding claims,' which specifies both the action and the unique deliverable (explaining unavoidable technical terms). This clearly distinguishes it from generic rewrite tools like tone_rewrite or grammar_edit among the siblings, despite not naming them. The main verb and resource are concrete.

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 implies its use case – whenever text must be made plain-language and technical terms explained – but does not explicitly contrast with alternatives such as tone_rewrite, metadata_rewrite, or content_localization that appear in the sibling list. It also states constraints ('no external research or outbound actions') that imply appropriate scenarios, but there are no explicit when-to-use / when-not-to-use conditions. This is reliable enough for an agent to infer, but not directly stated.

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