interactive_feedback

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool must be called repeatedly, that feedback content triggers adjustment and further calls, and that the tool returns a list of TextContent and MCPImage objects. It also discloses the [NEW TASK] behavior, which is beyond what annotations or schema would convey.

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 verbose and includes repetitive instructions ('must call this tool' appears multiple times). While it is well-structured with headers and numbered rules, it could be more concise. The inclusion of the full USAGE RULES block is necessary for the agent's behavior, but some redundancy could be trimmed 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?

Given that there is no output schema and only three parameters, the description is exceptionally complete. It covers when to use the tool, when to stop, how to respond to feedback, and how to handle task transitions ([NEW TASK]). It also explains the return format and provides project directory context. This is fully sufficient for an agent to invoke and interpret 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 coverage is 100% for all three parameters, so the baseline is 3. The description adds additional meaning by explaining that 'project_directory' helps the user know what was done and that 'summary' is for user review, which enriches the parameter context beyond the schema field descriptions. The 'timeout' parameter is also given a default value with intent (waiting for user feedback).

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 'Interactive feedback collection tool for LLM agents,' which clearly identifies the tool's purpose as collecting feedback. It uses a specific verb ('collect') and resource ('feedback'), and the usage rules clarify that it is for obtaining user feedback during tasks, distinguishing it from the sibling tool get_system_info.

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 USAGE RULES section explicitly states when to call the tool (during any process, task, or conversation, including asking, replying, and completing phased tasks) and when to stop (only when the user explicitly indicates 'end' or 'no more interaction needed'). It also provides context for handling [NEW TASK] prefixes and summarizes behavior for the next step. This is thorough and actionable.

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