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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, establishing safe read-only behavior. The description adds behavioral context by noting that 'get' provides authors, topics, summary, and download formats, and that report IDs follow a letter-number pattern (e.g., R40097). This enhances the agent's understanding of what to expect without contradicting the 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?

The description is two compact sentences with no redundancy. The first sentence establishes what CRS reports are, and the second explains the operations and ID format. The key actionable information (list vs get, ID format) is front-loaded, making it efficient for an agent to parse.

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 read-only tool with an output schema and well-documented parameters, the description adequately covers the essential usage details: the operations, the report ID format, and what 'get' returns. It doesn't mention pagination or error handling, but those are covered by the schema and the tool's read-only nature. Minor omission of how 'list' results are returned is tolerable given the output schema exists.

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 schema already documents all parameters with 100% coverage, including descriptions and defaults. The description adds value by specifying the concrete report number format ('R40097', 'RL33612', 'IF12345') and clarifying that reportNumber is required for 'get', which reinforces the schema's conditional requirement. This goes beyond the schema's generic wording.

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 clearly states the tool browses and retrieves CRS reports, explicitly describing them as nonpartisan policy analyses covering policy areas, legislative proposals, and legal questions. This distinguishes it from sibling tools for bills, committee reports, and other congressional documents, making the purpose unambiguous.

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?

The description provides explicit guidance on how to use the two operations: 'Use 'list' to browse available reports or 'get' for full detail'. It also clarifies the report ID format required for 'get'. While it doesn't explicitly contrast with sibling tools or state when not to use this tool, the topic distinction (CRS reports vs. other congressional documents) is implied through the description's content.

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