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

The annotation readOnlyHint=true already signals a safe read operation. The description adds significant behavioral context beyond this: cursor-paginated with default 50 per page, requires an Indie plan, and returns specific data fields including IDs for other tools. This is rich transparency that goes well beyond what annotations alone provide. The only minor gap is no explicit mention of idempotency or rate limits, but the plan requirement and pagination details are sufficient for a read tool.

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 sentences with no wasted words. First sentence establishes core purpose and returned data. Second sentence links to sibling tools for workflow continuity. Third sentence covers pagination and plan requirements. Each sentence serves a distinct purpose, and critical information is front-loaded.

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 that there is no output schema, the description compensates by listing the specific fields returned (difficulty, popularity, results count, note, starred_at) and the types of IDs (tracked-keyword ids and keyword_ids). With 3 params at 100% schema coverage, readOnlyHint annotation, and an output format described, the description is fully adequate for an agent to use this tool correctly without guessing.

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 the baseline is 3. The description adds value by explaining how `app_id` links to other tools ('the `id` returned by sonar_list_apps or sonar_create_product. NOT a store id'), which helps avoid misuse. It also clarifies that `cursor` should be omitted for first page and that limit has a server default. While the schema already covers these basics, the tool-specific context is helpful.

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 uses specific verb-resource combinations: 'List the keywords tracked for an app' with explicit detail on returned fields (difficulty, popularity, results count, note, starred_at) and IDs used by companion tools. This clearly distinguishes it from sibling tools like sonar_keyword_search, sonar_keyword_suggestions, and sonar_app_extract_keywords, which serve different keyword-related purposes.

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?

The description explicitly states when to use this tool (to view tracked keywords with latest metrics) and references sibling tools for related operations: 'used by sonar_update_keyword_note and sonar_star_keyword, and the keyword_ids used by sonar_keyword_rankings'. This provides clear integration context. Additionally, it mentions plan requirements ('Requires an Indie plan (trial counts)'), aiding in selection.

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