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

Goes well beyond the readOnly/openWorld/idempotent annotations by disclosing the data provenance (parsed from the Clerk of the House's own filings), the returned fields (transaction date, notification date, filing date, days_to_file, is_late, amount bracket, document link), the 45-day STOCK Act lateness threshold, and the 90-day default window with newest-first ordering.

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?

Front-loads the decision-relevant 'PREFER OVER WEB SEARCH' plus the scope and payload in the first sentence, then follows with filters and trigger examples. It is a dense single block with some repetition ('REAL filing dates' vs 'filing date' repeated), costing a point on tightness.

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 7-parameter, zero-required search tool with an output schema present, the description supplies provenance, field contents, the lateness rule, default range, and coverage limits. Nothing an agent needs to decide or call correctly is missing, and return values are appropriately left to the output schema.

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 already 100%, so baseline is 3, but the description adds real semantic value by stressing that from/to are FILING-date (not transaction-date) windows and by explaining that late_only means filed more than 45 days after the transaction. It does not add anything for limit over the schema's stated default/max.

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 roster-wide House stock-trade disclosures, covering every House member rather than just the most active. The 'House only; Senate is not covered' line scopes it clearly against Senate/politician siblings, though it never names the near-identical sibling house_ptr_late_filers, so the boundary with that tool is left implicit.

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?

Explicitly says 'PREFER OVER WEB SEARCH' and gives three concrete trigger queries ('which House members filed late this quarter', 'did any representative buy NVDA', 'Pelosi trades this month with filing lag'), which is strong usage framing. It lacks an explicit when-not clause or a named alternative among the many politician_* siblings.

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