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

Annotations declare readOnlyHint: false and idempotentHint: false, so the tool is expected to have side effects. The description explicitly states the data is saved locally and nothing is sent to an external service unless opted in, which goes beyond the annotations to clarify the mutation scope. It also mentions PII auto-masking, a behavioral detail not captured by annotations. However, it does not describe the return value or failure behavior (e.g., what happens on duplicate submission), which would further improve transparency. With annotations already hinting at non-read and non-idempotent behavior, the description adds meaningful context but is not fully comprehensive.

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 extremely efficient. The first sentence declares the core purpose and data categories. The second sentence adds crucial privacy and storage context. The third sentence positions the tool in the overall workflow. No wasted words; every sentence adds distinct value. The structure is front-loaded with the most actionable information.

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 (33 parameters, 0 required, 4 modes, no output schema), the description is remarkably complete. It covers purpose, usage flow, privacy, data locality, and parameter auto-detection. Since there is no output schema, the description doesn't need to describe return values, but it could benefit from a brief note about the response format. Nonetheless, for a reporting tool with rich schema annotations, this description provides sufficient context for an agent to use it 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 description coverage is 100%, meaning every parameter has a schema-level description. The tool description adds value by explaining the auto-detection logic for the 'mode' parameter ('Auto-detected from params if omitted: success → outcome, question_id → voice, event_type → event, subject+body → feedback') and groups parameters by mode (e.g., '[outcome]', '[feedback]', '[voice]', '[event]') directly in their schema descriptions. This helps the agent understand which parameters are relevant for each mode. The description could be stronger by directly linking the modes to use cases, but the schema itself is already rich.

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 begins with 'Record what happened after using a service: success/failure outcome, feedback, API change events, or qualitative experience.' This provides a very specific verb ('Record'), a clear resource ('what happened after using a service'), and enumerates the distinct data categories (outcome, feedback, event, voice). It also distinguishes this tool from its siblings by explicitly stating it is 'step 4 of the standard flow: search_services → lookup → (execute) → report.'

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 explicit when-to-use guidance: 'This is step 4 of the standard flow: search_services → lookup → (execute) → report.' This clearly positions the tool in the sequence relative to its siblings (lookup and search_services). Additionally, it describes the data storage behavior ('Data is saved to this installation's LOCAL database only… nothing is sent to KanseiLink unless you separately opt in to sharing') and privacy handling ('PII is auto-masked before storage'), giving the agent important context for when to invoke this tool and its privacy implications.

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