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

Annotations provide readOnlyHint=true and title, which already indicate a safe read operation. The description adds the pagination behavior (cursor-based, default 100 per page) and the plan requirement (Indie plan/trial counts) – neither is deducible from annotations alone. The description does not contradict annotations. A 4 is warranted because while the description adds useful behavioral context, it doesn't detail what happens if the plan is exceeded or how cursors expire.

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 three sentences long, each carrying distinct value: what data is returned, how the results are used, and pagination/plan details. No wasted words. Front-loaded with the primary purpose.

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 naming the output fields (rating, review count, version, installs) and mentioning the pagination cursor. However, it does not fully describe the response shape (e.g., total count, error format) or the exact structure of each snapshot. It is nearly complete for a list tool, but lacks confirmation of whether all fields are always 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 coverage is 100%, so the baseline is 3. The description adds value by specifying the default page size (100) and that the cursor is obtained from a previous call's `next_cursor`. It also clarifies that omitting cursor fetches the first page. These semantic details go beyond the schema's generic descriptions. A 4 reflects the added context without being exceptional.

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 a clear verb ('List') and specific resource ('apps tracked in the caller's Sonar workspace') including what kinds of apps (own + competitors) and what data each comes with (latest snapshot fields: rating, review count, version, installs). This is easily distinguishable from the many sibling tools like sonar_get_app (single app) or sonar_track_app (adding tracking).

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 that this tool returns the Sonar app UUIDs needed as input for four other tools (sonar_get_app, sonar_app_keywords, sonar_app_rankings, sonar_app_changes) and specifies that results are cursor-paginated with a default page size of 100. It also mentions the plan requirement (Indie plan or trial). No alternative tool is suggested for a different use case, but the dependency chain is exceptionally clear.

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