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

Annotations already supply readOnly, idempotent, and openWorld hints. The description adds meaningful behavioral context beyond those: it states that name search is not supported, that currentMember=true restricts to currently serving members, and that 'list' filtering follows specific combination patterns. No contradiction with annotations.

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?

Three sentences carry a large amount of operational guidance without fluff. The most important scoping caveat ('No name search') and the filtering rules are front-loaded, and the workflow progression from list to get/sponsored/cosponsored is logically structured.

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 an 8-parameter tool with four operations, the description covers filter combinations, required dependencies, operation selection once bioguideId is known, and an explicit exclusion. Combined with a 100% described schema, rich annotations, and an output schema, nothing essential is missing for an agent to invoke it correctly.

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 baseline is 3. The description adds value by clarifying relationships: district requires stateCode, stateCode can pair with congress, and bioguideId is the key for get/sponsored/cosponsored. Concrete examples (e.g., 'CA district 12 in the 118th') reinforce parameter semantics beyond dry schema text.

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 the resource ('congressional members and their legislative activity') with a clear verb ('Discover') and immediately delimits scope with 'No name search.' It also names the four operation modes, making the tool's purpose and boundaries obvious relative to sibling lookup tools.

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 explicit usage patterns for the 'list' operation—filter by stateCode, optionally with district, by congress, or both—and explains when to switch to 'get' or 'sponsored'/'cosponsored' once a bioguideId is known. It doesn't explicitly compare to sibling tools, but the domain and operation guidance are clear enough for correct invocation.

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