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

Annotations indicate readOnlyHint=false and destructiveHint=false, so it's not read-only, but the description doesn't disclose potential side effects like overwriting existing plans or creating duplicates. It does mention auto-creation of article suggestions, but lacks details on idempotency or confirmation requirements.

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 a single dense paragraph that front-loads the core action and adds a parenthetical list of exclusions. It's concise but could benefit from bullet points for readability.

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 (harvesting logic, exclusions) and no output schema, the description is reasonably complete, but it doesn't mention response format, potential errors (e.g., if research isn't complete), or how the resulting plan is accessed. Those could be inferred from sibling tools.

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?

With only one parameter (projectId) and 0% schema description coverage, the description doesn't explain the parameter at all. However, projectId is self-explanatory given the tool's purpose. The description mentions criteria like top-30 and exclusion thresholds, which add context beyond the schema but not parameter-specific semantics.

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 it creates a content plan by harvesting top-30 opportunity clusters and auto-creates article suggestions, distinguishing it from siblings like set_opportunity_status and set_excluded_terms which are referenced as excluded inputs.

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 implies usage after a completed research run and explicitly mentions what is excluded, but does not explicitly state when not to use it or mention prerequisites like having a project with completed research. It could better contrast with sibling tools like list_opportunities or accept_idea.

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