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

Annotations already declare readOnlyHint and idempotentHint. The description adds valuable behavior: response format (speaker turns with timecodes) and pagination handling. These are beyond annotation scope and help the agent predict output and next steps.

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?

Two sentences with no filler. The core purpose is stated first, followed by the response shape and pagination. Every sentence contributes essential information.

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 an output schema present, the description covers key aspects: source of ID, response content, and pagination. It omits error scenarios, but for a read-only idempotent tool with annotations and schema, this is adequately 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 100%, so parameters are documented. The description augments this by explaining when cursor should be used (when has_more is true) and clarifies that transcript_id comes from a prior get_engagements call, adding practical context not in the schema.

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 reads a single transcript by transcript_id, sourced from get_engagements. This distinguishes it from siblings like get_deal or get_engagements, 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?

Provides explicit context that transcript_id comes from get_engagements and gives a concrete instruction for pagination (call again with cursor when has_more is true). It does not explicitly contrast with alternatives, but the source linkage and pagination guidance are sufficient for typical usage.

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