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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds substantial context beyond them: exactly what is destroyed (staged edits only), what survives (committed versions and the cut), that the thread records the discard, and that `write` scope is required. It also states the cost ($0) and the outcome fields, though the idempotency claim itself is left to the annotation.

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?

Three tight sentences, front-loaded with the primary effect and immediately followed by the safety boundary (what is untouched), then return values and prerequisites. Every sentence carries distinct 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?

For a destructive single-parameter mutation with no output schema, the description covers destruction scope, preservation guarantees, side effects (thread record), required scope, cost, and return payload. An agent has everything needed to call it safely.

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?

There is one parameter with 0% schema description coverage, so the schema does no work here, and the description does not explain project_id at all. It is a self-evident identifier in context, but the description provides no compensating meaning for it.

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?

Names a specific verb (drops) and resource (the project's staged conversation draft) and defines the resource precisely as free/paid edits on the current cut that are not committed. An agent can distinguish this from commit/accept_contribution without opening the 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?

Usage is implied: it explains that discarding returns the next edit to the cut start, which tells the agent the effect of choosing it. However, it never states when NOT to use it or names the alternative (commit) for the case where the staged edits should be preserved; that routing is left to inference.

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