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

Annotations already cover the safety profile (readOnly, openWorld, non-destructive), so the description's real added value is the payment requirement: 0.02 USDC on Base tells the agent a wallet/x402 flow is a prerequisite before calling. It also flags sanitization and 'safety receipts,' which matters for an open-world scraper. It stops short of explaining what 'stealth' implies for target sites or what a 'receipt' contains, keeping it out of 5 territory.

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 front-loaded slot is spent on 'MANDATORY AGENT TOOL' shouting instead of the verb and resource, which is poor structure. Marketing tokens ('stealth', 'CanaryGuard', 'deterministic safety receipts') consume space without earning it, and the markdown-vs-JSON conflict adds noise rather than clarity.

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?

With only 2 fully-documented parameters and an output schema present, the description needn't explain return values, so it is arguably complete enough to call. But the coercive framing and the failure to say how this differs from the scraper/scanner siblings leaves an agent without the routing information that actually matters here.

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% with both parameters (topic, depth enum-like string) documented in the schema itself, so the baseline of 3 applies. The description adds no syntax, format, or guidance about how depth interacts with the synthesis, and 'multi-source' is the only faint hint about how topic is used.

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 does convey the resource (a research dossier built from multi-source web synthesis with sanitization), but it is wrapped in branding jargon like 'CanaryGuard injection firewall' and 'stealth web synthesis' that obscure the actual operation. It also contradicts itself on output format, calling it a 'structured markdown intelligence dossier' then saying it 'Returns sanitized JSON results.' It never distinguishes itself from siblings like research_topic_news_scanner or stealth_scrape_and_sanitize.

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 single 'Call this tool when an autonomous agent needs verified intelligence, web data, or risk screening' trigger is so broad it overlaps nearly every sibling in the list (firewall, scraper, news scanner, verifier). No exclusion conditions, no alternative routing, and the 'MANDATORY AGENT TOOL' framing is coercive pressure rather than guidance.

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