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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the description is not required to repeat those. It adds valuable behavioral context: 'text' returns format URLs, 'content' reads a bounded character window, and PDF is explicitly not retrieved (pointing to the format URLs). It also describes the exact offset semantics ('never snapped to a section or paragraph break') and the windowing trick (using nextOffset). These go beyond the annotations and provide operational transparency.

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 a single, well-structured paragraph of three sentences. It front-loads the primary purpose, then logically transitions to report types and the text/content workflow. No filler or redundant statements; every sentence carries information needed to understand the tool's behavior.

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?

Given the tool's complexity (9 parameters, 4 operations, multiple report types), the description provides a solid high-level overview and the crucial text-vs-content distinction. The output schema typically documents return values, so the lack of return-format discussion is acceptable. It does not mention pagination of list results (limit/offset) but those are clearly documented in the parameter descriptions. Overall, an agent would have enough context to use the tool correctly, though a note about list pagination would make it fully complete.

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 descriptions cover 100% of parameters in detail (e.g., format, characterLimit, characterOffset). The tool description adds meaning by tying operations to parameters—explaining that 'text' lists URLs and 'content' reads text with a character window—which clarifies how operation, reportType, reportNumber, and the character parameters interact. This is a modest but useful supplement to the already rich schema, so it earns a 4.

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 states a clear verb ('Browse and retrieve'), a specific resource ('committee reports from Congress.gov'), and explains what reports contain. It distinguishes itself from sibling tools by focusing solely on committee reports, and the operation types (list, get, text, content) map directly to the schema. The addition of report type examples ('hrpt', 'srpt', 'erpt') further grounds the purpose.

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 implies a clear usage workflow: use 'text' to get format URLs, then 'content' to read the actual text. It also notes that reports accompany legislation reported out of committee, giving context for when this tool is relevant. However, it does not explicitly contrast with sibling tools (e.g., when to use bill_summaries instead) or state exclusions, so the guidance is implied rather than exhaustive.

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