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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description reconciles this with the 'delete' name by explaining the tool performs no mutation and opens no browser session. It also adds useful context beyond annotations: the return is screen/button/field-level instructions and the account is the user's own. It stops short of describing output format nuances or failure modes, so it is strong but not exhaustive.

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 routing information is front-loaded and useful, but the trailing sentence about AccuRanker's official API and MCP server ("checked 23 Oct 2026") is tangential to invoking this tool and reads as residual noise. The sentence structure is also clause-heavy, cramming return behavior and follow-on tooling into one breath.

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 zero parameters and no output schema, the description carries the burden of explaining the return value, and it does so concretely ("step by step (screens, buttons, fields)"). The read-only, non-opening nature is spelled out, which is exactly what an agent needs before chaining into cotlet_browser_* calls; only the handoff mechanics (which browser tool to start with) remain implicit.

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 and the baseline of 4 applies. No parameter-level claims are made that could mislead.

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?

"Delete keywords in the user's own AccuRanker account" gives a specific verb and resource, and the follow-up sentence clarifies that the tool itself only produces step-by-step instructions rather than performing the deletion. The apparent mismatch between the name 'delete' and the actual read-only behavior is resolved inside the description, so an agent can tell what it gets back, though the first sentence alone is misleading until the second is read.

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 states the follow-on path explicitly: use the cotlet_browser_* tools in the user's AccuRanker Cloud Browser after receiving the steps, and it states what not to expect ("opens nothing by itself"). It does not explicitly contrast with sibling accuranker_add_keywords or list_keywords_and_ranks, but the delete-specific routing is clear enough to act on.

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