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

Annotations already declare readOnlyHint=true, and the description adds that it returns 'year-level score, verdict, adverse alerts, and element dimensions', which is useful context about the output. There is no contradiction. The behavioral constraint (window) is also disclosed.

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?

Two sentences, no fluff. First sentence clearly states purpose and return content. Second sentence provides sibling differentiation and constraints. Every sentence is valuable and front-loaded.

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 no output schema, the description gives a high-level overview of return fields (score, verdict, alerts, dimensions). It covers main usage, constraints, and sibling relationships. Could elaborate on output structure, but sufficient for an agent to understand when to call.

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%, so the schema already documents all parameters adequately. The description does not add parameter-level details beyond what the schema provides, leading to a baseline score 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 this tool returns year-level outlook for a full calendar year, with specific examples of user queries ('how is 2026', '今年怎么样'). It distinguishes from sibling tools by explicitly mentioning month and day alternatives, and includes a window constraint (currentYear-1 to currentYear+1).

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 states when to call ('when the user asks about a full calendar year as a whole') and when not to ('For month precision use intentions_ask_month; for day use intentions_ask_day'). Also provides a behavioral constraint (window limited to currentYear±1).

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