keystone_target_add

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

No annotations are provided, so the description carries the full burden. It explicitly discloses overlay semantics: only the region between `<!-- BEGIN KEYSTONE -->` and `<!-- END KEYSTONE -->` is rewritten, preserving pre-existing user content. This is a significant behavioral detail that goes beyond a simple 'install' statement.

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 appropriately sized with four sentences, each adding value: purpose, what menu files are, overlay semantics. It is front-loaded with the main action and does not waste words.

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?

The description covers the core behavior and critical overlay semantics, and an output schema exists so return values need not be described. However, it does not explain what the 'force' parameter does or any prerequisites (e.g., whether the harness must already exist), which is a minor gap given the tool's complexity.

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?

The description adds meaning for 'agent' (whose menu files) and 'project_root' (install location), but 'force' is not explained at all. With 0% schema description coverage, the description partially compensates but leaves a gap for the force parameter's behavior.

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+location: 'Install the agent's menu file(s) at the project root.' This clearly states what the tool does and mentions menu files (CLAUDE.md, AGENTS.md) which distinguishes it from siblings like keystone_harness_bootstrap. It is not vague or tautological.

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: menu files are thin pointers to the harness and MCP server, so the tool is used to install these lightweight pointers. However, it does not explicitly compare with alternatives or state when not to use it, making it a 4 rather than a 5.

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