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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds a genuinely useful return-behavior fact with no output schema present ('every row has a source filing link') plus the breadth of ranking dimensions, though it says nothing about result-set size, auth, or rate limits.

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 scope enumeration is front-loaded in the first sentence and the usage trigger is last, so the agent gets the what before the when. The single long list is dense but each element earns its place by expanding a vague free-form parameter; slight repetition of 'top' is the only waste.

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, the description compensates by noting source filing links per row, and with one fully documented parameter the schema burden is low. It is nearly complete, but for a tool sitting among twelve heavily overlapping siblings it should have clarified its relationship to quarter_rankings, state_lobbying, industry_lobbying, and revolving_door.

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 topic parameter already carries examples, so the baseline is 3. The description goes further by enumerating valid topic dimensions the schema does not spell out (most lobbied agencies, former government officials, fastest-growing firms, defense/tax/appropriations issues), which meaningfully disambiguates the free-form topic string.

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 names a specific resource (ranked lists from lobbying filings) and enumerates the exact ranking dimensions returned: top firms by income, top spenders, top lobbyists by client count, former officials, fastest-growing firms, most lobbied issues/agencies, sliced by year, issue, industry, or state. An agent can tell this is the general-purpose rankings tool rather than a single-entity lookup like get_firm or get_lobbyist.

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?

It gives an explicit routing trigger: 'Use for any "top", "biggest", "leading" or "best-known" lobbying question,' which maps directly onto how ranking queries are phrased. It stops short of naming alternatives or exclusions, so overlap with quarter_rankings, industry_lobbying, state_lobbying, and revolving_door is left unresolved.

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