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

Annotations already declare read-only/idempotent/non-destructive, so the bar is low, and the description clears it comfortably: it discloses cursor pagination with a default page size of 50, the Indie-plan requirement, and the provenance semantics of `popularity` (apple vs proxy, floored Apple readings, null on Android). That is non-obvious behavioral context an agent cannot get from the schema or 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?

Front-loads purpose and return fields before the domain detail, with no filler sentences. The popularity paragraph is dense and long, but each sentence carries semantics an agent would otherwise misread, so it earns its space even if it could be broken into shorter clauses.

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 does the work of explaining the returned record shape (difficulty, popularity variants, results count, note, starred_at, ids), plus pagination and plan gating. An agent can call this correctly and interpret the response without further reference.

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 100%, so baseline is 3, but the description adds a detail absent from the schema: the concrete default page size of 50 (the schema only says 'server default applies'). It also clarifies that `keyword_ids` and tracked-keyword ids come back from this call, which frames how pagination params are used.

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 and resource (list tracked keywords for an app) and enumerates the returned fields, so the scope is unambiguous. It never explicitly contrasts itself with the keyword-related siblings (sonar_keyword_metrics, sonar_competitor_keywords, sonar_discovered_keywords), so sibling differentiation is only indirect via the downstream-id mentions.

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?

Usage is implied rather than stated: the description tells you the ids feed sonar_update_keyword_note, sonar_star_keyword, and sonar_keyword_rankings, which helps an agent place the tool in a workflow. It gives no explicit when-to-use/when-not versus the other keyword-listing tools, though it does add the practical prerequisite that an Indie plan is required.

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