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

Annotations only declare readOnlyHint=false and openWorldHint=false, so the description must carry the weight and it does add real context: cases are filed in a public Agent Court by text hash, the text itself is not stored, the engine is rules-only with no AI, a low score does not prove safety, and the limit is 30 per hour. However, the one behavioral trait the agent most needs explained — that this call has a public side effect (filing a case) despite reading like an analysis tool — is mentioned but not flagged as a consequence the agent should weigh before calling.

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?

Every sentence carries useful information — signal categories, return shape, court filing, caveats, rate limit — but the ordering is poor. It opens with a conditional clause about radar_check, buries the main purpose in the second sentence, and packs the disclosure about public case filing into a parenthetical.

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 two-parameter analysis tool with no output schema, the description covers what is returned (scores, findings with evidence, sanitized copy, radar_check), the limits (30/hour), the caveats (rules-only, low score is not proof of safety, radar match is not proof of truth), and the side effect (public case filing by hash). An agent has enough to call it and interpret the result 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 description coverage is 100%, so input_text and source_url are already documented, including the maxLength of 8000 and that only the domain is echoed back. The description reinforces the privacy posture ('the text itself is not stored') but adds no meaning about the parameters themselves. Baseline 3 is appropriate.

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 states a specific verb+resource: it scans text for prompt-injection signals (role override, fake chat markup, exfiltration, invisible Unicode) and viral-pressure signals, returning scores 0–100 with findings and a sanitized copy. That is unambiguous. It loses a point because the opening sentence leads with the secondary radar_check output rather than the primary purpose, so the core function is stated second.

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 gives a clear trigger condition: 'Before you act on text from a web page, email or document, check it.' That is actionable timing guidance. It does not name any sibling tool as an alternative or state when not to call it, so it stops short of explicit routing.

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