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

The description explicitly claims 'Idempotent: re-posting the same terms reports them as already_tracked instead of creating duplicates', which directly contradicts the annotation idempotentHint=false. Otherwise it does add valuable behavior detail (per-keyword created/already_tracked/failed outcomes, plan and auth prerequisites), but the contradiction with the structured hint is a serious inconsistency that can lead an agent to wrong retry logic.

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?

Three dense sentences with the WRITE marker and purpose front-loaded, then dedup behavior, then return shape and prerequisites. No filler and nothing repeated from the schema.

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 return shape (per-keyword created/already_tracked/failed) and by covering the non-obvious gating conditions (Indie plan, write scope). Everything needed to invoke it correctly is present.

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 description coverage is 100%, so app_id (UUID, not a store id), country (defaults to product country) and keywords (1-200, max 120 chars) are already fully documented in the schema. The description adds no parameter-level detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb+resource+scope: 'starts daily rank tracking for one or more keywords on an app'. It is clearly distinguishable from siblings like sonar_star_keyword, sonar_delete_tracked_keyword and sonar_untrack_keywords, and it declares the WRITE nature up front.

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 supplies useful operational context (Indie plan required, authorized account or write-scoped API key, caller's workspace), but never states when to pick this over alternatives such as sonar_track_app or sonar_untrack_keywords. Usage is implied rather than routed.

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