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

Annotations already declare readOnlyHint=true, so the description doesn't need to restate that. It adds useful behavioral context: results are limited to tracked apps, keywords are not yet tracked, rows are classified into buckets, and results are ordered by an opportunity score (0-100, best first). It also discloses the plan requirement, which is valuable operational information.

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 deliver the core value proposition, result categories, key metrics, ordering, and the recommended next action. There is no filler, and the plan requirement is included without bloating the text. Every clause adds 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?

With no output schema, the description compensates by naming the returned fields (popularity, difficulty, AI relevance, opportunity score) and the ordering. It also gives a complete workflow: read this list, pick winners, track them. It doesn't mention default filters or pagination, but the parameter schema covers those, and the read-only annotation covers the safety profile.

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 input schema covers all 8 parameters with full descriptions and enum values at 100% coverage, so the schema already handles parameter semantics. The description adds context about returned fields like opportunity score but doesn't need to repeat individual parameter docs. Baseline 3 is appropriate because the schema does the heavy lifting.

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 returns discovered, untracked keywords from Sonar's discovery engine for tracked apps, with specific categories (ranked finds, competitor gaps, AI/autocomplete ideas) and metrics. It distances itself from generic keyword tools by positioning it as the 'what should I track next' list and references the natural follow-up tool.

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 explicitly says when to use this tool: as the discovery/next-tracking decision source, and directs the user to sonar_track_keywords for the next step. It also notes the Indie plan requirement. It doesn't explicitly compare against related keyword-research siblings like sonar_keyword_suggestions or sonar_competitor_keywords, so it misses the full when-not-to-use guidance.

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