set_config

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

With no annotations, the description carries the behavioral burden, and it delivers: it discloses that settings propagate to every provider layer and that repo scope overrides global for a single repo. It could add more about merge-vs-replace semantics or return/error behavior, but the core side-effect profile is clearly stated.

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?

Two sentences contain the essential behavioral model and scope semantics with no fluff. The central propagation fact is front-loaded, and the global/repo override rule follows immediately.

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 setter with a rich nested schema and an output schema, the description plus schema is sufficient to call the tool correctly. Minor gaps are the lack of explicit mention that config is merged (though the schema says 'settings to merge in') and no direct guidance on branch/project parameters, but those are documented in the schema.

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%, so the baseline is 3; the description adds real semantic value by explaining what scope=global and scope=repo actually do, which the schema's generic 'Where the settings apply' does not. It does not re-describe every config key, which is appropriate since the schema already documents them.

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 and resource ('Configure preferences') and immediately clarifies the central, propagating nature of the operation. The scope=global vs scope=repo distinction makes the tool's behavior and scope unmistakable and differentiates it from the read-only get_config sibling.

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 context for when to choose global vs repo scope, including the effect of each ('writes the spec that applies to all repos' vs 'overrides it for this repo only'). It does not explicitly name alternatives or exclusions, but the usage context is strong enough for an agent to apply it correctly.

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