Prepare transcript save

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the agent knows this is a non-idempotent, non-destructive write. The description adds that the operation is only 'staged' rather than committed, and that no audio is captured or played, which is genuine extra context. It still omits whether a confirmation step is required and whether repeated staging risks duplicate entries.

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 tight sentences, with the core action stated first and the audio exclusion immediately after. Nothing is redundant and every clause carries information the agent needs.

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 and a mutation tool, the description covers the primary behavior and the audio misconception well. It does not explain what 'staging' produces (e.g., a pending action id) or how to complete the save, which is a meaningful gap for a prepare/confirm-pattern tool.

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 description coverage is 0%, so the description must compensate. It explains the 'role' enum by saying 'user or assistant transcript,' which maps directly to that field's enum. The 'content' and 'session_id' parameters receive no explanation of format, limits, or purpose, leaving a partial gap against the low coverage.

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 gives a specific verb+resource: 'Stage saving an already-created user or assistant transcript into ReceiptCal chat history.' It also clarifies the scope negatively with 'This does not capture or play audio,' which matters given the 'voice_transcript' name. It stops short of differentiating itself from the many other 'prepare_*' siblings, but the purpose itself is 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 phrase 'already-created' implies the transcript must exist before calling, and 'does not capture or play audio' rules out audio-handling use cases. However, it never states that this is a two-phase operation requiring a follow-up confirm_action, nor points to any alternative tool. Usage is implied rather than stated.

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