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

Beyond the minimal annotations, the description discloses important side effects: auto-creating the content plan, landing suggestions in generating_brief, automatic brief forging, free-tier queueing past the daily cap, and duplicate-title skipping. These are exactly the behavioral details an agent cannot infer from readOnlyHint/destructiveHint.

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?

Four dense sentences each earn their place: the core operation, how to obtain inputs, the side-effect warning, and the return value. No filler or repetition of schema 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?

For a state-changing tool with no output schema, it covers the required call sequence, side effects, duplicate behavior, free-tier constraints, and return value. An agent has enough context to select and invoke 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 coverage is low at 17%, so the description compensates by explaining where key parameter values come from: angles from expand_radar_topic and signalObservationId/topicIndex from list_radar_topics. It also gives projectId context via plan auto-creation. The optional topicAngleTotal still relies on its name and schema, so the compensation is strong but not exhaustive.

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 a specific action: adding selected radar-topic angles to the content plan as radar-born article suggestions. It adds distinguishing scope details—provenance preserved and exact-title duplicates skipped—and clearly differentiates this from generic suggestion tools by linking it to expand_radar_topic.

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?

It gives a concrete invocation path: call list_radar_topics first to obtain signalObservationId and topicIndex, and take angles from expand_radar_topic. It also provides an explicit exclusion—do not also call generate_article_brief—so an agent knows when to avoid a sibling tool.

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