kernel_agents_feedback

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

There are no annotations, so the description carries the full behavioral burden. 'The agent learns from feedback to improve future runs' does disclose a persistent side effect, which is worth something, but it says nothing about what is stored, whether the rating overwrites prior feedback for the same run, whether lesson text becomes long-term memory, or what permissions are required 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?

Two short sentences, with the action stated first and the rationale second, and nothing wasted. The second sentence is slightly promotional ('improve future runs') rather than informative, which keeps it just below the top mark.

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 four-parameter mutation tool with no annotations and no output schema, the definition is thin. It omits any note on what happens after submission, whether the call is idempotent per run_id, or how it relates to the many overlapping feedback and learning siblings.

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 description coverage is 100%, so all four parameters (run_id, rating, lesson, outcome) are already fully documented in the schema, including the 1-5 rating scale and the outcome enum. The description adds no additional meaning such as how lesson interacts with future runs or how outcome differs from rating. Baseline 3 applies.

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: 'Rate an agent run and provide feedback.' That is clearly distinct from read-oriented siblings like kernel_agents_history or kernel_agents_list. It does not, however, differentiate itself from the overlapping feedback/learning siblings such as kernel_brain_feedback or kernel_agents_add_learning.

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?

No when-to-use or when-not-to-use guidance is given, and no prerequisites are stated (for example, whether the run must be complete before rating it). Several sibling tools also persist learning, yet the description never indicates which one an agent should pick in a given situation.

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