darknet_investigate

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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds substantial beyond that: bounded redacted evidence with provenance and explicit coverage, the single-page fetch semantics of fetch_onion, an explicit negative list (no crawling, new scans, raw documents, malware downloads, invented risk score), and a prompt-injection warning that provider claims are untrusted data. This is unusually rich 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?

Four front-loaded sentences: purpose first, then what it returns, then the read-only constraints, then the security caveat. No filler, and the ordering lets an agent decide relevance from the first sentence alone.

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 exists, yet the description tells the agent what comes back (bounded redacted evidence, provenance, explicit coverage, shared indicators), what it will not do, and how to opt into onion fetching. For a high-fan-out aggregator with five params this is complete enough to invoke 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% and every parameter already carries its own enum/range/bounds documentation, so baseline is 3. The description adds genuine meaning beyond the schema for fetch_onion ('fecthes the supplied page once', default metadata-only, never follows links), nudging it above baseline.

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 (Investigate) plus the full set of accepted resource types (domain, email, IP, hash, URL, v3 onion, Bitcoin address, CVE) and frames itself as spanning 'all eight dark-web and threat-intelligence capability families.' This clearly positions it as the cross-family aggregator versus the many single-purpose siblings like btc_address or onion_lookup.

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 establishes when this tool applies broadly (one investigation across all capability families) and constrains the risky mode ('explicit fetch_onion opt-in fetches the supplied page once'; 'Only existing-source lookups'). It doesn't explicitly route the agent between this umbrella tool and the granular siblings (e.g. when to prefer pulsedive_indicator over this), so it stops short of full when/when-not guidance.

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