feedback_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 of behavioral disclosure. It transparently states the timing of feedback delivery (next planning step or on resume) and the special effect of kind='pin' or 'rejection' with a target on hypothesis state. This goes beyond the schema. However, it does not mention potential failure modes or prerequisites like session existence, leaving some gaps.

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 two sentences with no wasted words. It front-loads the primary purpose and immediately provides the timing and state-change nuance. Every clause adds value, making it highly concise and well-structured.

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?

Given the tool's complexity (session state dependency, hypothesis mutation) and the lack of annotations or output schema, the description covers the key behavioral aspects. It could be more complete by specifying that the session must exist or what happens on invalid input, but it is adequate for a tool with this scope. The absence of return value documentation is acceptable since no output schema is provided.

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 75% (three of four parameters have descriptions; kind only has an enum). The description adds semantic value by explaining the interaction between kind and target for moving hypothesis state, which is not present in the schema. This compensates for the missing description of kind, justifying a score above the baseline of 3.

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 injects researcher feedback into a session, with a specific verb and resource. It differentiates from siblings by focusing on feedback injection rather than session control (like session_pause) or hypothesis recording (like hypothesis_record). The mention of how it affects hypothesis state further clarifies its unique role.

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 contextual usage: it explains when the feedback takes effect (running vs paused sessions). It does not explicitly name alternative tools or state when not to use it, but the behavioral context is sufficient for an agent to infer the appropriate use case. Since sibling tools like review_record or match_record are not referenced for exclusion, this is not a 5.

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