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

Annotations already state readOnlyHint=true and destructiveHint=false; the description adds useful non-obvious behavior: chart facts are computed server-side, the widget card renders, narrative fields are explicitly AI-generated, and the assistant should add only text the card does not already display. 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?

Two dense, focused sentences. The core purpose appears first, followed by the card-rendering behavior and then the brief output-steering instruction. Each sentence carries useful content; there is no filler.

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 complexity, the annotations, and the presence of an output schema, the description covers the important call-and-response flow. It explains current/looking-up-year marking, narrative sourcing, and post-card behavior. The only noticeable gap is fuller clarification of how focusYear and asOfYear map together, though this is partly inferable.

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 description adds meaning by identifying focusYear as a year with its 세운 and narrative as AI-written card text. However, with schema description coverage at 40%, it does not compensate for undocumented parameters such as asOfYear, focusNote, birth, and the details of birth environment fields.

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 identifies the specific action and resource: 'Render the 대운 flow timeline' and shows what the rendered output contains (current 대운, optional focus year with its 세운). The parenthetical list of marriage/job-change/business-start timing questions distinguishes it from other saju card tools.

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 tells when the tool is relevant: 대운 flow, marriage timing, job change or business-start questions. It also gives an integration rule: narrative fields should be grounded in a prior legend_saju_read_fortune call. It does not explicitly name alternative tools and when not to use this one, so it misses the top score.

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