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

With no output schema, the description carries the return contract itself: 'up to 5 registrants', the type/dates/status fields, how foreign principals are represented (named vs withheld as a count), and the three parallel federal record streams with their sources. It also warns against the most likely misuse — adding FARA receipts, LDA counts and PAC contributions together, and reading a PAC match as a foreign-client link.

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?

Purpose is front-loaded in the first sentence, but the body is a dense run-on chain of disclaimers. Several sentences (country strings not being a statement of U.S. foreign policy, the quoted DOJ approval language) serve legal caution rather than tool selection or invocation and dilute the operative instructions.

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 one-parameter, no-output-schema, high-complexity tool, it covers what comes back, what is never matched, and what the numbers mean. Remaining gaps are minor: no explicit statement of what an empty result looks like beyond 'no match is a search result', and no guidance on narrowing overly broad substrings.

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 100% and the single parameter is fully documented in-schema (case-insensitive, max 80 chars, published registrants only), so the description adds little. What it does add — 'substring', 'among the published registrants' — restates the schema rather than extending it.

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?

Opens with a concrete verb+resource+access path: 'Look up a registered foreign agent in the Foreign Agents Register by registrant name substring'. The name-substring lookup mode implicitly separates it from foreign_agents_country / foreign_agents_principal / foreign_agents_summary siblings, but it never names those alternatives explicitly.

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 implied by the search mode ('by registrant name substring', 'among the published registrants'), and it does state a scoping limitation (individuals and single-person firms are withheld). But there is no explicit when-to-use / when-not, and no routing to the sibling foreign_agents_* tools that cover the same dataset from other angles.

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