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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds genuinely non-obvious behavioral context: DOJ's counts differ from the entries its listing prints and are never reconciled, the series is a separate measure never summed with others, no individuals are named, and registration is not a finding of wrongdoing. It does not describe return shape or ordering, but the provenance and reconciliation caveats are exactly the misuse-preventing information annotations cannot carry.

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 core content list is front-loaded and informative, but the description is one sprawling sentence-plus-caveats with noticeable redundancy: 'separate measure', 'never reconciled', 'never added to them' and 'shown as DOJ's' all restate the same non-comparability point. The verbatim legal quotation is defensible but lengthens an already dense block.

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 parameters and no output schema, the description carries the burden of telling the agent what comes back, and it does so by enumerating the series and their source reports and date coverage. An agent can call this correctly with no further information; only the exact response shape (nesting by half-year, field names) remains unspecified.

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 tool takes zero parameters, so there are no semantics to document and the baseline is 4. The description correctly implies a fixed, unfiltered snapshot (by half-year, 2024-2025) rather than a queryable resource, which is the one thing a caller needs to know about the absent inputs.

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 states a specific resource and scope: DOJ's FARA administration and enforcement figures from four semi-annual reports for 2024-2025, broken out by half-year, and enumerates the contained series (inspections, civil causes, criminal count, statistical summary). It distinguishes itself from adjacent measures (FARA receipts, LDA counts, PAC contributions), but never names a sibling tool such as foreign_agents_summary or foreign_agents_country, so the agent must infer routing from the topic labels 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 implied by the content list: call this when you want DOJ's own enforcement counts rather than registrant-level data. The description warns it must never be added to receipts, LDA or PAC numbers, which is a useful exclusion, but it never states when to prefer a sibling tool or what a caller must already know (e.g., that only 2024-2025 are covered).

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