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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds the traits an agent cannot infer: defanged input is silently refanged, output can optionally be re-defanged, the call costs $0.002 USDC per *successful* call via x402 on Solana, and an equivalent HTTPS endpoint exists. Cost, payment rail and the input-normalization side effect are exactly the kind of non-obvious behavior this dimension rewards.

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?

A single dense paragraph that front-loads the core verb and the indicator taxonomy before secondary details (defang, price, endpoint). The type list is long but every item is functional; only the HTTPS endpoint line is arguably auxiliary for MCP callers.

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?

There is no output schema, so the description must carry return-shape information, and it only implies structure (defanged indicators) without saying whether results are grouped by type, deduplicated, or carry counts. Input handling, cost and payment are fully covered, so this is adequate but with a visible gap for a 17-type extractor.

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 75% (baseline 3), but the description genuinely adds meaning: 'private ranges optional' explains includePrivate, 'output can be defanged for safe sharing' explains the defang flag's purpose, and the type enumeration maps onto the types array. The only parameter not further illuminated is the 2,000,000-char text limit, which the schema already carries.

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 (extract) and resource (indicators of compromise) and then enumerates the seventeen indicator classes covered, so an agent knows exactly what it returns. It is clearly distinguishable from generic siblings like entity_extract or pii_detect because the enumeration is security-specific (CVEs, ATT&CK IDs, defanged URLs, crypto addresses).

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 names the input contexts that suit it: threat reports, alerts, logs and emails, which is a clear when-to-use signal. It does not name an alternative tool or state when-not-to-use (e.g. versus pii_detect or secret_scan for non-IOC extraction), so it stops short of full routing guidance.

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