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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is covered. The description still adds real value beyond them: it discloses that the tool opens nothing itself and only produces an instructional walkthrough (screens, buttons, fields), which is critical because the name otherwise implies a live search action. It could go further on what the returned steps look like in practice, but the key behavioral surprise is disclosed.

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 core operational fact (returns steps, opens nothing, then use cotlet_browser_*) is reasonably front-loaded in the first two clauses. But 'from ChatGPT, Claude or any AI agent' is filler, and the trailing sentence about Spotify's Web API and an official Claude connector dated 23 Apr 2026 / checked 5 Nov 2026 is extraneous trivia that does not help an agent decide or call the tool.

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, no output schema, and annotations covering safety, the description has a low bar. It meets it on the write-nothing / then-browse handoff, but leaves open how the target song or artist is specified with zero input schema, and does not hint at the shape of the returned instructions. For a tool whose name promises search but whose behavior is guidance, that gap matters.

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 the baseline is 4, but the absence of any query argument is itself a semantic question an agent will have: how is the target song or artist conveyed? The description never addresses this and implies the intent is inferred from conversation. Since there is nothing to document and no compensation for the missing query input, this sits just below the baseline.

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 names a specific resource (songs and artists in the user's own Spotify account) but then defines the operation as returning step-by-step UI instructions rather than performing a search, which conflicts with the name and title's 'search' framing. It does differentiate itself from the cotlet_browser_* siblings by saying it 'opens nothing by itself', but an agent cannot tell from this whether the tool searches, guides, or both.

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?

There is an explicit handoff instruction ('then do it with the cotlet_browser_* tools in the user's Spotify Cloud Browser'), which gives the agent a clear follow-up action. However, it never says when to pick this over spotify_read_playlist_songs, cotlet_app_guide, or the other Spotify siblings, and gives no conditions under which it should not be called.

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