decisions

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

Annotations already declare readOnlyHint=true, but the description adds behavioral context by detailing that it joins rule intervention, user execution, and post-hoc results with adoption rate summarization. No contradiction with annotations.

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?

Description is two sentences, front-loading the main purpose. It includes both a general statement and specific query examples, which is slightly redundant but not overly long. Could be slightly more concise.

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 presence of an output schema, the description adequately covers the tool's functionality (joins, summaries, specific answers). However, it fails to document the input parameter, which is a gap for a complete understanding. Overall adequate but with a clear missing element.

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?

The only parameter 'days' has no description. Schema coverage is 0%, and the description does not mention what the parameter controls or its default of 90 days. This is a significant gap as the parameter likely affects the time range of the view.

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?

Description clearly states it provides a unified decision view with joins and summaries, and lists specific questions it can answer. This distinguishes it from siblings like 'explain_decision' (single decision) and 'run_committee' (creation).

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?

Description gives explicit usage context by listing the types of questions it answers (e.g., 'how many times did I listen to suggestions'), helping users know when to invoke it. It does not explicitly mention alternatives or when not to use, but the specificity is helpful.

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