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

While annotations already flag destructiveHint=true, the description adds substantial context beyond them: exact cascade semantics, the detachment of shared sources, default-branch rejection, the version persisted with the summary label, the returned counters, and read-only key exclusion.

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?

Dense and front-loaded: each clause carries a distinct fact (scope, shared-source rule, precondition, return fields, version, auth). No filler sentences; nothing could be removed without losing 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?

With no output schema, the description enumerates the return fields, and it covers preconditions and side effects for a destructive multi-entity mutation. Nothing an agent needs to invoke this safely appears to be missing.

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% and the description compensates: it clarifies that dataset_id identifies the branch being deleted and that summary labels the persisted version. The undocumented model_id is only weakly covered ('Not advertised to read-only keys' implies key scoping but doesn't explain the model_id requirement).

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 opens with a specific verb+resource ('Deletes a branch') and immediately details the cascade scope (input rows tagged with the dataset_id, exclusive data sources, detachment for shared sources). This distinguishes it sharply from layerz_update_branch and the other branch/model siblings.

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 gives clear conditions: the default branch is rejected and read-only keys don't see it, and it explains the shared-source detachment rule. It stops short of explicitly naming an alternative (e.g., update_branch) for the case where a delete isn't wanted, so it's strong context but not full when/when-not routing.

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