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

Annotations already declare a non-read-only, non-destructive, closed-world write. The description adds real behavioral context beyond them: this is a partial update that leaves every other branch untouched, new branches start unpublished, and the caller must be an owner. It does not describe the response, but everything about the effect of the call is disclosed.

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 clauses, zero filler, with the create-or-update distinction and the effect scope front-loaded. Nothing could be cut without losing meaning.

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 9-parameter mutation tool with no output schema, the definition is missing what comes back — notably whether the new branch's id is returned, which the agent would need for the follow-up make_branch_live call. It also does not say whether name is effectively required when creating, despite required-parameters being empty.

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 100% and every parameter is documented inline (id create-vs-update, enum for kind, length caps, alias examples). The description only restates the id semantics already in the schema, adding no extra syntax or constraints, so baseline 3 applies.

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+resource with upsert semantics: 'Add a branch, or change one (give its id)'. It also scopes the effect ('every other branch stays'), which is the key distinction from bulk siblings like make_branches_live or undo_bulk_edit, though no sibling is named explicitly.

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?

Clear selection rule for the two modes: omit id to add, supply id to change. It also flags the prerequisite ('Owner only') and the post-condition that a new branch is not public until made live, which implicitly routes the agent to make_branch_live. No explicit when-not-use guidance or named alternative beyond that inference.

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