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

The annotations only say readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden. It adds useful traits: it returns a config, wraps exactly one unit of work, and treats an empty endpoint as agentic execution. It does not contradict the annotations, though it doesn't spell out whether the configuration is persisted or just returned.

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 well organized: definition, kind semantics, parameter relationships, and a UI note. The parenthetical about the Rokha UI is marginally useful context but not essential for an agent. Overall, it is front-loaded and every substantive sentence earns its place.

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?

With 6 optional parameters, nested params, no output schema, and minimal annotations, the description covers all the key decision points: what kind means, how to specify a tool call, what empty endpoint does, and what the tool returns. Nothing needed for correct invocation is missing.

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, but the description adds real value beyond the schema by explaining how parameters relate: endpoint + tool + params together constitute a live tool call, empty endpoint means agentic, and 'instruction' is an imperative step. This helps an agent assemble the parameters correctly rather than just knowing their names.

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 specific action ('Configure a Harness'), the resource, and the core distinction between 'skill' and 'instruction' wrappers. It goes beyond the bare title by explaining what a harness is and what the tool returns ('get back its config'), making it distinguishable from siblings like get_harness, list_harnesses, and delete_harness.

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 gives clear internal guidance: use 'skill' for a registry skill, 'instruction' for a pure agent step, set endpoint+tool+params for a real live tool call, and leave endpoint empty for agentic execution. It does not explicitly contrast harness_author with create_harness or update_harness, but the purpose and branching conditions are clear enough for an agent to select and invoke correctly.

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