Search SGU segments (timecoded)

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

No annotations are provided, so the description carries the full burden. It describes a read-only search operation but does not explicitly state it is non-destructive or safe. It lacks disclosure about result ordering, pagination, or performance implications, which are typical for search tools.

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 four sentences, front-loaded with purpose, then contrast, use cases, and optional filters. Every sentence adds value without redundancy. No wasted words.

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 5-parameter, 1-required tool with no output schema, the description is nearly complete. It explains the function, return fields, and filters. Missing are details about result sorting, default behavior, or any limitations, but overall sufficient for effective use.

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 schema already documents parameters well. The description adds minor context (e.g., speaker examples 'Steve', 'Cara') but does not significantly enhance understanding beyond the schema. Baseline of 3 is appropriate.

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 this is a fine-grained full-text search over individual speaker turns, contrasting with search_episodes which returns whole episodes. It lists specific return fields (episode, date, segment, timestamp, speaker, snippet), making the tool's purpose and output 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 explicitly tells when to use this tool ('find the moment when…', quoting, narrowing within an episode) and contrasts it with search_episodes. It mentions optional filters but does not specify when not to use or other alternatives among the 12 sibling tools.

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