preview_reply

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

The description adds meaningful behavioral context beyond the readOnlyHint and destructiveHint annotations: it confirms no paste/send side effect and discloses that semantic privacy classification is not enforced server-side. This is useful operational caveat information that annotations alone would not convey.

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 compact, front-loaded with the core purpose, and every sentence adds value: the no-send guarantee, client prerequisites, and privacy limitation. There is no redundant or filler content.

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?

The description omits essential parameter semantics and has no output schema to explain the draft return format. It gives useful server-side caveats and preconditions, but a 3-required-parameter tool with zero schema coverage needs more explicit input/output guidance to be safely invocable.

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 carries the full burden of explaining session_id, observation_id, and text, but it does not define any of them. 'Latest observation' loosely relates to observation_id, yet the role of text and session_id remains unexplained, and the requirement of text is confusing given the tool 'returns' a draft.

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?

Description states a specific verb ('Return'), a clear resource ('unsent draft for the latest observation'), and explicitly disambiguates by saying it does not paste or send anything. This makes the tool's purpose immediately distinguishable from sibling tools like acknowledge_observation or poll_changes.

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 provides clear preconditions and context: the client must first identify new incoming text, merge bursts, and skip privacy questions. It does not explicitly name alternative tools or state when not to use it, but the usage context is concrete enough for an agent to decide when this preview step is appropriate.

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