Update the agent's settings

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

With no annotations, the description carries the full burden. It discloses that it makes a local file change and that cs_push is required to apply it, which is useful behavioral context. It also differentiates file locations by harness. However, it does not mention whether changes are merged or overwritten, whether an existing agent is required, or any side effects beyond the file edit. These gaps limit transparency for a mutation tool.

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 dense but not overly verbose, packing a lot of information into a single sentence. It front-loads the core action ('Edit agent.mcs.yml') before listing settings. While it could be split for readability, the length is justified given the 17-parameter complexity. Every clause adds value.

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?

Given the tool's complexity (17 params, nested objects, enums) and lack of output schema, the description covers most essential context: file locations, harness variants, and the need to push changes. It does not explicitly state that the agent must already exist, but that is inferred from sibling tools and the update verb. Overall, it is complete enough for correct invocation.

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 59%, and the description adds significant semantic value by grouping parameters into meaningful categories (e.g., 'response instructions (wording and formatting)', 'capability toggles (web browsing, code interpreter, image generation...)'). It also explains the operational context ('Local file change; cs_push applies it') not present in the schema. This helps an agent understand the impact of parameters beyond their raw definitions.

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 states a precise verb ('Edit') and the exact resource ('agent.mcs.yml'), lists the specific settings it can change, and distinguishes between standard and Copilot harnesses. It clearly differentiates from sibling tools like cs_create_agent (creation) and cs_update_settings (generic settings) by specifying it updates agent configuration files.

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 explains when this tool is used: to edit agent settings locally, and notes that 'cs_push applies it,' indicating the workflow. It also provides harness-specific guidance ('For GitHub Copilot harness... settings.mcs.yml'), which helps select the right target. However, it does not explicitly state when not to use it versus alternatives, though the context is clear.

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