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

Annotations declare readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious context beyond them: the tool returns human-readable steps (screens, buttons, fields), performs no action itself, and requires a separate browser-tool call to actually complete the task. This is important because the name implies a write. It does not cover prerequisites such as what happens if no Brandfolder account or browser session is connected.

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 behavior is front-loaded in the second sentence, but the first sentence largely restates the title and the trailing 'Brandfolder's official API: Yes.' is dangling metadata that gives the agent no actionable information. The middle sentence is dense and slightly awkwardly punctuated ('... opens nothing by itself; then do it with ...'), costing readability.

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 most of the burden, and it does explain the shape of the return (step-by-step screens/buttons/fields) and the follow-up path. Only failure modes (account not connected, browser session unavailable) are unaddressed, which is a modest gap for a zero-argument advisory tool.

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 input schema has zero parameters, so there is nothing for the description to disambiguate; baseline for a no-parameter tool is 4. The description's account scoping ('user's own Brandfolder account') is the only parameter-like constraint and it is stated.

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 (share link) and a specific scope (the user's own Brandfolder account), and explicitly corrects the misleading verb by stating it 'Returns how to do it in Brandfolder step by step ... and opens nothing by itself.' That resolves the create/read tension so an agent knows this is an advisory tool, not a mutator. Minor noise ('from ChatGPT, Claude or any AI agent', 'Brandfolder's official API: Yes') dilutes but does not obscure the purpose.

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?

Clear workflow context: call this to get the step-by-step procedure, then execute it with the cotlet_browser_* tools in the user's Brandfolder Cloud Browser. This tells the agent both when to use it and what to do next. It stops short of naming exclusions or explaining when a different brandfolder_* sibling would be preferable, so it is strong context without full routing guidance.

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