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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds value beyond that: amounts are separate nullable USD strings (not one aggregate), disclosure text is untrusted record data (a prompt-injection warning), and issue_code is applied post-fetch rather than upstream. It does not cover rate limits or page-budget interaction with max_pages.

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?

Four sentences, front-loaded with the primary capability before filter details and caveats. Dense and telegraphic in places ('Native filters include posting dates, reported amounts, client location and foreign entities'), but essentially every clause carries operational information.

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 27 optional parameters, an output schema, and full schema descriptions, the description supplies the remaining pieces an agent needs: the two invocation modes, cursor-based paging, local-vs-native filtering, and data-trust caveats. Paging budget behavior (max_pages/page_size defaults and clamps) is left entirely to the schema, which is a minor gap.

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%, so the baseline is 3; the description earns above that by explaining filter semantics the schema does not, specifically that issue_code filters activities locally and cannot narrow upstream requests, and that amounts are separate nullable strings. Several parameter groups (paging, record_*) are only described in the schema.

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 and resource ('Search federal lobbying registrations and activity reports') plus a second mode ('retrieve a complete filing by filing_uuid'). The two-mode structure lets an agent distinguish search vs. fetch, but it never names or contrasts the nearby siblings such as uslobbying_search_lobbyists or uslobbying_search_foreign_agents.

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 real routing context: filing_uuid mode is for retrieving complete records from evidence or analytical selections, and 'Follow next_cursor for all versions' tells the agent how to page to completion. It also warns that issue_code filters locally and cannot narrow upstream requests, which prevents a wrong usage pattern. Missing only explicit when-not-to-use guidance against sibling search tools.

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