onboard_agent

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

With no annotations, the description carries the full burden. It discloses idempotency (fenced markers + version skip no-op writes), file modification (project configuration files), the mandatory user consent requirement, and the return structure. It does not mention if existing rules are overwritten, but the idempotency and versioning hint at safe behavior. This is good coverage for a mutating 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 well-structured: a one-sentence purpose, a mandatory consent warning, a concise parameter list with mode behavior, and a returns section. It is slightly longer than necessary due to repeating some parameter details that are also in the schema, but every section earns its place with the consent warning and mode logic being critical.

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 tool with 4 parameters, no annotations, and no output schema, the description covers all essential context: idempotency, consent, create/update mode behavior, parameter interactions, and the exact return format. It lacks error handling details (e.g., what happens if no context file exists and target_agent is omitted), but the description is sufficient for an agent to invoke the tool correctly in most scenarios.

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%, but the description adds context beyond the schema: it clarifies that files defaults to recommendation.target_files in update mode, that files is ignored when target_agent is provided (create mode), and specifies the exact condition for target_agent requirement. This adds practical meaning to the parameters, going beyond the schema descriptions.

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 starts with 'Write or update the kontexta workflow rules block in a project's agent context file(s)' – a specific verb+resource that clearly distinguishes from generic file tools like update_file. It names the exact domain (kontexta workflow rules) and the target (agent context files), leaving no ambiguity about what the tool does.

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 context on when to use the tool: it explains create vs update modes, when files is ignored, when target_agent is required, and the mandatory consent step. However, it does not explicitly compare to sibling tools like update_file or create_file, so an agent may not know why to choose this over those alternatives. The guidance is strong but not fully explicit about alternatives.

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