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

Since no annotations are provided, the description carries the full burden and breaks it admirably. It discloses the exact lookup over 365 days, aggregated fields, archive block semantics, the non-overlapping window statement, the auto-detection fallback and the security warning that fields are untrusted. No key behavioral quirk appears hidden.

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 description is longer than average but the length is earned by the tool's branching behavior: exact query, archive window, substring fallback, and data-safety warning. It is front-loaded with the main purpose and maintains logical structure; still, some parenthetical details about aggregated returned fields could be trimmed without hurting correctness.

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 and no annotations, this description covers the critical context an agent needs: when each branch executes, what data is returned, edge-case conversion, and an input-specific warning. It is sufficiently complete for a one-parameter tool whose complexity lies in lookup behavior rather than in output structure.

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?

The schema already covers the value parameter completely by describing auto-detection types, but the description adds meaningful extra semantics beyond that baseline: defanged input acceptance, http/https variants, the 30-day window for domain/URL metadata, and the distinction of domain/url-only enrichment. This gives the invoker more insight than the schema alone.

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 opens with a specific, actionable verb phrase: 'Look up an IOC value in TweetFeed.' It differentiates itself from siblings like check_hash, check_ip, and check_url by emphasizing auto-detected IOC types, exact-match enrichment, and substring fallback, so an agent can distinguish this broader enrichment tool from the narrower periodic checks.

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 clearly states the lookup sequence (exact 365-day match first, then substring fallback) and the conditions under which the archive block is included, which gives strong usage context. It does not explicitly name sibling tools or say when to prefer a dedicated check_hash/check_ip/check_url tool, so it misses the 'versus alternatives' level of guidance.

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