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

Annotations only cover safety hints (writes, non-idempotent, non-destructive), so the description carries the important behavioral load: it re-validates coherence with the same blocking/non-blocking report the human sees, force overrides a blocking report, and the operation requires `write` scope and is `$0`. These are substantive traits beyond what annotations provide.

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?

A single dense sentence that front-loads the core action and the resulting state, then appends the two option behaviors and cost/auth facts. No filler and each clause earns its place.

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 mutation tool with no output schema, the description covers the state transition (`isHead: true` in the answer), the gating behavior, the branch alternative, the required scope, and cost. An agent has everything needed to call it correctly.

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 coverage is 67% – force and as_branch already have descriptions – but the description sharpens them with concrete semantics ('overrides a blocking report', 'keeps the new version as a branch ... where it can become the cut later'). project_id remains undocumented in both places, keeping it from a 5.

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 ('commits') and resource ('staged conversation draft as a new version') and clarifies the resulting state ('makes it THE CUT the production line renders'). The agent can distinguish this from siblings like set_head or cancel 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?

Clearly signals the precondition (a staged draft) and the two behavioral modes (force to override a blocking gate, as_branch to keep it as a branch instead of the cut). It stops short of explicitly naming when to use set_head instead, so routing against siblings is implied rather than spelled out.

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