baron_scm_write

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

The description explains important behavioral aspects: branch_create is idempotent, pr_create's linkedIssueRelation semantics, and that a provider-declined merge surfaces as MERGE_FAILED rather than a false success. This is valuable since no annotations are provided, and it goes beyond just listing parameters.

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?

The description is concise given the complexity (5 operations, 15 parameters) and organizes information per operation with parentheses. It front-loads the overall purpose. A minor improvement would be breaking into a list for readability, but it remains compact.

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 complex tool with 15 parameters and no output schema, the description provides sufficient context for each operation's semantics and parameters. It covers idempotency, merge failure behavior, and link relations. The only gap is the response format (e.g., what is returned on success), but with no output schema, the description could include that.

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 very low (7%), so the description must compensate. It does so by grouping parameters per operation and explaining semantics for key parameters (fromBranch, linkedIssueKey, linkedIssueRelation, strategy, deleteSourceBranch). However, some parameters like body, draft, assignees, autoComplete are only mentioned in passing without full detail.

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 clearly identifies the tool's purpose as changing source-control state and lists the five distinct operations with their required and optional parameters. It distinguishes itself from siblings like baron_scm_read (which likely reads state) and other baron tools focused on issues, recipes, or memory.

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?

The description provides clear guidance on when to use each operation and the effect of parameters (e.g., 'closes' finishes the item on merge, 'relates' only references it for linkedIssueRelation; 'idempotent' for branch_create). However, it does not explicitly contrast with baron_scm_read or other siblings for deciding when to write vs. read.

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