search_transcripts

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds valuable behavioral context: it returns sentence-level matches with speaker attribution and timestamps, and it mentions the >30-day narrowing requirement (a performance/scope behavior). No contradictions 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, each earning its place: purpose, usage/alternative guidance, and a critical constraint plus output summary. No fluff, front-loaded with the core action. It is concise yet information-dense.

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?

Despite no output schema, the description communicates the return format ('sentence-level matches with speaker attribution and timestamps') and the key scoping constraint. It also differentiates from 14 siblings. Minor gaps include lack of pagination details or error behavior, but for a read-only search tool with a well-annotated schema, this is sufficiently 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?

Schema coverage is 90%, so most parameters are already described. The description adds meaning beyond the schema by tying keywords to an ad-hoc use case, and by specifying that primaryUserIds/domains are required for narrowing when date ranges exceed 30 days—a constraint not evident from the individual parameter descriptions. This enriches the parameter semantics.

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 opens with a clear verb+resource: 'Free-text keyword search across call transcripts within a bounded date range.' It explicitly differentiates from sibling tools by framing this as the ad-hoc transcript search while pointing to search_calls + get_call_summary for recurring tracker-based searches. The example 'calls mentioning competitor X' concretely illustrates the intended use.

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?

Provides explicit when-to-use ('Use for ad-hoc searches') and when-not-to-use ('For recurring terms, prefer... Trackers'), naming specific alternative tools. It also gives a critical operational constraint ('Date ranges > 30 days require additional narrowing via primaryUserIds or domains') that informs parameter decisions. This is model-tier guidance.

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