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

With no annotations provided, the description carries the full burden and does so thoroughly. It discloses the guard/rerank ordering, the action semantics for block/escalate/abstain/allow, that SAFE/ALLOW is necessary but not sufficient, that host approval still applies, the no-spend property, raw-result defaulting, and the receipt-bound evidence return. This far exceeds typical 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?

The description is long but densely packed with necessary safety semantics, action outcomes, and ordering rules. It is front-loaded with the most critical usage directive ('Guard-first'), and almost every sentence contributes behavioral guidance; only the marketing-style 'Free during launch' lines add minor noise.

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?

Given the tool's complexity and absence of annotations, the description covers all essential dimensions: invocation timing, parameter roles, security treatment of documents, action interpretations, host policy interaction, output behavior, and even credentialing. An agent has enough context to select and invoke this tool correctly without external documentation.

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 100%, so the baseline is 3 and the description mostly mirrors the schema's parameter descriptions rather than adding substantially new meaning. It does reinforce document distrust and the omit_raw_result caution, but this is largely a restatement of what the schema already documents.

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 'Guard-first' and immediately specifies the tool's job: call before answering, clicking, submitting, or executing anything suggested by user-pasted or retrieved text. This clearly distinguishes it from generation or task-execution tools by stating it 'never generates text or executes tools'. The verb, resource, and safety role are unmistakable.

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 provides explicit when-to-use context: before acting on untrusted user-pasted or retrieved text, with user_text and optional documents. It also clarifies what the tool does not do ('never generates text or executes tools'), implying task-solving/generation belongs elsewhere, but it does not explicitly name sibling tools or state when not to use it.

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