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

Annotations already confirm read-only safety, but the description adds important behavior: transcripts can exceed a million characters, so the tool returns a bounded window with offset/max_chars/next_offset, or search returns every matching passage. It also clarifies that transcript_url is the official document.

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 front-loaded with purpose and then explains the large-transcript handling. It is dense with useful information, though slightly long and could be broken into clearer sentences for faster scanning.

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 must explain return behavior, and it does: the hearing, transcript window, next_offset, search passages with offsets, and transcript_url. It also covers edge cases like missing transcripts and oversized documents.

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 the baseline is 3. The description adds useful semantics beyond the schema: offset and next_offset form a continuation loop, max_chars bounds the window, and search switches to phrase-based passage retrieval rather than a linear window.

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—'One committee hearing or meeting'—and includes the endpoint. It distinguishes itself from siblings by naming list_hearings and get_committee for finding hearing_id, and explains that the tool returns the hearing plus transcript content.

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 tells the agent how to obtain hearing_id via list_hearings or get_committee include:['hearings'] and when to use the windowed read versus the search mode. It also notes that transcripts exist only where has_transcript indicates and gives examples of venues that carry them.

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