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

The annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=true and destructiveHint=false, so the safety bar is low; the description still adds real value by stating "opens nothing by itself," which confirms the tool is a pure lookup of instructions with no browser side effects. It also discloses the split architecture (this tool plans, browser tools execute), which an agent would otherwise have to discover by trial. It does not say whether a SoundCloud session must already exist in the Cloud Browser, which is the main remaining behavioral unknown.

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, but the second is a sprawling construction that chains the return value, the no-side-effects guarantee, the follow-on tools, and the API justification with semicolons. The most decision-relevant fact — that this returns a how-to, not the counts — is not front-loaded and is buried mid-sentence. It could be split into three short, ordered statements.

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 parameters and no output schema, the description carries the burden of explaining what comes back, and it does name the return shape (screens, buttons, fields). What it omits is that with zero inputs the guide must be generic, so the agent gets no signal about how track-specific selection happens — presumably during the browser phase. Adequate for a simple guide tool, but the boundary between guide and execution is left for the agent to infer.

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 tool takes zero parameters, so there is no parameter semantics to explain and the schema is trivially complete. Baseline 4 applies. The description cannot add parameter meaning here, and it correctly does not fabricate any.

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 eventually states the real behavior — it returns step-by-step instructions ("screens, buttons, fields") rather than the counts themselves — but the leading sentence and the tool name/title both say "Get play and like counts," which is what an agent will latch onto first. The actual purpose has to be reverse-engineered from the second half of a run-on sentence. A reader can figure it out, but the framing actively points the wrong way.

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 does prescribe the follow-on workflow ("then do it with the cotlet_browser_* tools in the user's SoundCloud Cloud Browser") and explains why the official API is a dead end (Artist Pro required to register an app), which is genuinely useful routing context. However, it never says when to call this versus a sibling like soundcloud_list_tracks or soundcloud_check_if_you_messaged_a_profile, nor what to do if the guide doesn't cover the case at hand. Usage is implied rather than conditioned.

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