create_branch

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds genuine context beyond them: that the source snapshot is never mutated (copy semantics) and that the premise field captures an intention rather than a realized event. This clarifies behavioral intent that structure alone doesn't 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?

Three short, front-loaded sentences with essentially no filler; the core action leads and qualifications follow. The premise sentence is slightly cryptic in isolation but is dense rather than wasteful.

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 state-mutating creation tool with 5 required parameters and no output schema, the description omits almost everything an agent needs to call it correctly: what is returned, uniqueness/conflict behavior on branch_id or idempotency_key, and the meaning of most parameters. It is more complete than a stub but not adequate given 0% schema documentation.

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% across 6 parameters, so the description must compensate and largely doesn't. It only adds meaning for two of them (premise as an intention, from_revision via "current or historical"), leaving campaign_id, branch_id, name, and idempotency_key entirely undocumented in both places.

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 concrete verb and effect ("Fork a current or historical snapshot") plus the consequence ("Copies point-in-time knowledge"), which is enough for an agent to understand it creates a new derived branch. It does not, however, explicitly name itself as the branch-creation tool or distinguish it from siblings like list_branches or restore_checkpoint.

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?

It implies the operation forks a snapshot (current or historical), but gives no when-to-use condition, no prerequisites, and no mention of alternatives such as restore_checkpoint. The result is that the agent must infer usage context from the name alone.

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