agent_feedback

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

Annotations only set readOnlyHint=false and idempotentHint=false, but description adds important behavioral context: 'Append-only' (non-destructive, no updates) and constraints like 'maxItems: 20' for reasonCodes. However, doesn't detail what happens on duplicate submissions or error behavior.

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 front-loaded with the core purpose, then gives usage guidance and parameter semantics in a structured way. While comprehensive, it could be slightly more concise without losing meaning.

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 7 parameters (4 required, arrays, enums) and an output schema, the description covers the purpose, usage constraints, parameter roles, semantics, and behavioral traits. It leaves no significant gaps for an agent to use the tool correctly.

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 has 0% description coverage, but the description compensates by explaining grade semantics ('full = helped complete the task, partial = somewhat useful but flawed, no = wrong or wasted the turn') and listing starter reason codes for each grade. It also explains referencedToolName and referencedRequestId, but misses projectId and projectRef fields.

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 clearly states the tool's purpose as an 'append-only feedback tool for rating a prior Mako tool run from the agent perspective'. It distinguishes itself from the sibling 'agent_feedback_report' by being the writing tool.

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?

Explicitly advises to 'Use sparingly when a result was notably good, notably bad, or wrong; do not emit routine feedback after every call', providing clear when-to-use and when-not-to-use criteria. Also specifies that it 'Requires referencedToolName and referencedRequestId so each row is tied to a specific prior run'.

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