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

Annotations only declare readOnlyHint=false and idempotentHint=false; the description supplies the non-obvious cost model the agent cannot infer: the preview runs the normal paid model work and consumes one generation allowance, exactly like the real call. It also states the write boundary ('nothing is written to the library') and a concrete downstream consequence (no Post id), which corroborates and enriches the non-idempotent hint.

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?

Four short sentences, front-loaded with what the tool does, then cost, then downstream handling, then the sibling routing rule. There is no filler or redundant restatement of the name.

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 cost-incurring, non-saving variant of generate_post with no output schema, the description covers the behavior, cost, and follow-up workflow well. It is only incomplete on the nested 'voice_overrides' object and the enum parameter, which the agent would have to guess at.

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 description adds no meaning about any of the five parameters; it only refers to the output 'content' conceptually. Schema coverage is 60%, and two of the uncovered parameters are the riskiest: 'style' has an empty description despite a five-value enum, and 'voice_overrides' is a nested object with no description at all. The description does nothing to compensate for those gaps.

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?

States a specific verb and resource ('Create a Jack preview') and immediately bounds it ('without saving a Post'), which cleanly separates it from the sibling generate_post. An agent can identify the operation and its output shape (a preview with no Post id) without opening any schema.

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?

Gives an explicit selection rule against the alternative: 'Prefer generate_post when the Jack will probably be kept,' which implies the inverse for discardable previews. It also names the follow-on path (schedule_post, export_to_tap) for the case where the preview turns out to be worth keeping.

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