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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses the critical non-obvious behavior: a paid endpoint ($0.35 USDC via x402 on Base), the exact failure mode (PaymentRequired challenge on unpaid calls) and the retry contract (resubmit identical call with signed payload in _meta["x402/payment"]). It also reveals the fan-out behavior across six endpoints. This is exactly the kind of behavioral context annotations cannot convey.

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?

Front-loaded purpose, then returned artifacts, then price and payment mechanics in order of likely need. Dense but each sentence carries distinct information; no filler.

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 no output schema, the description compensates by listing the returned artifacts (profile, infrastructure analysis, IOC table, detection rules, kill chain, MITRE ATT&CK coverage). Combined with the payment contract and fan-out disclosure, an agent has everything needed to call and interpret the result.

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% (the actor param is documented with concrete examples like SANDWORM, XENOTIME, VOLTZITE). The description adds no additional meaning about the actor parameter, so the baseline 3 applies.

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 and resource ('Comprehensive intelligence dossier for an ICS threat actor') and enumerates the underlying endpoints and returned artifacts, making clear it is the broad aggregation call. It does not name or differentiate against the very close siblings getActorReport and getThreatActor, so an agent must infer the distinction from 'Comprehensive'/'Deep' alone.

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?

Usage is only implied: the broad fan-out and 'Comprehensive' framing suggest this is the deep, all-in-one call versus narrower siblings like getActorReport. There is no explicit when-to-use, when-not-to-use, or named alternative, and no prerequisite guidance beyond the payment flow.

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