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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the safety profile is covered. The description adds real value beyond that: it discloses the return content (step-by-step UI instructions) and the fact that the tool performs no action itself, which resolves the apparent tension between the name "Delete" and the read-only annotation. It could be more blunt that no deletion occurs, since "opens nothing by itself" is slightly indirect.

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?

Front-loaded with the action and scope, then the mechanism and the execution path. The final sentence about no public REST API or webhooks is useful context but marginally tangential to invoking the tool, and the "from ChatGPT, Claude or any AI agent" phrasing is filler.

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?

For a zero-parameter, no-output-schema tool, the description covers what it returns (UI steps) and what it does not do (no browser opening, no API call). Missing only practical preconditions such as whether the Ubersuggest Cloud Browser must already be connected or the account logged in.

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 meaning to explain; the empty schema with additionalProperties=false is self-explanatory. Baseline 4 applies since nothing is missing on this dimension.

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?

States a specific verb and resource ("Delete tracked keywords in the user's own Ubersuggest account") and immediately clarifies the actual mechanism: it returns step-by-step instructions rather than performing the deletion. This distinguishes it from siblings like ubersuggest_add_tracked_keywords and from the cotlet_browser_* execution tools.

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?

Explicitly routes the agent: call this to get the Ubersuggest screens/buttons/fields, then perform the action with the cotlet_browser_* tools in the user's Cloud Browser. It also states the tool "opens nothing by itself," preventing a wrong assumption about side effects. It stops short of naming prerequisites (e.g., browser app already open, logged-in session) or when-not-to-use conditions.

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