voice_get_new

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

With no annotations, the description carries the burden of disclosure. It transparently reveals that the tool does not auto-advance the checkpoint (by instructing to use set_checkpoint) and returns a 'potential checkpoint index' for later use. This conveys key read-only behavior implicitly, though it doesn't mention error handling or edge cases.

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 two short, front-loaded sentences. Every sentence adds value: the first states the core purpose, the second explains the return content and points to the companion tool. 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 no-argument tool with an output schema, the description covers the main behavior and workflow sufficiently. It explains what is returned (new text and checkpoint index) and how to integrate with set_checkpoint. Lacks details about no-checkpoint behavior but that is a minor edge case given the output schema exists.

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 tool has zero parameters and the schema coverage is 100% effectively. The baseline for zero parameters is 4, and the description adds relevant context about the checkpoint index which relates to the tool's behavior rather than parameters, so no deduction is needed.

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 'Get text transcribed since the last checkpoint.' This specifies a unique verb and resource, and distinguishes it from sibling tools like voice_get_text (which likely returns all text) by anchoring on the checkpoint mechanism.

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 instructs using voice_set_checkpoint to mark read content, providing a clear workflow. It doesn't explicitly mention when not to use, but the pointer to the complementary sibling tool gives solid contextual guidance.

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