Extract indicators from text

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

With no annotations, the description carries the burden and does well: it discloses that the tool is offline (no external lookups or data exfiltration), that results are stable and deduplicated (idempotent output), and what categories are returned. It omits the concrete return shape (e.g., list vs. grouped-by-type) and any error behavior for text with no indicators.

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?

Two sentences, no filler. The indicator enumeration is front-loaded and the trailing clause adds use-case value rather than restating the tool name.

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 single-parameter, annotation-free, no-output-schema tool, the description covers input domain, extraction scope, and output character (stable, deduplicated). The remaining gap is return structure, but with no output schema and a self-evident list-of-indicators result, this is minor.

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?

Only one parameter with 100% schema description coverage, so the baseline is 4 by rule. The description adds domain framing ('a scam message or case') that clarifies what kind of 'text' is appropriate, which is a small value-add over the schema's 'Message or case text.'

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 ('stable, deduplicated indicators') and then enumerates the exact indicator classes (URLs/domains, phone numbers, wallets, IFSC, Telegram handles, etc.). This makes it immediately distinguishable from siblings like check_url or check_message, which validate rather than extract.

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?

Gives clear usage context: input is a scam message or case, and the output is useful for building blocklists or a case file. It does not explicitly name alternatives (e.g., 'use check_url to score a URL you already have') or state when not to use it, so it stops short of the top band.

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