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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description's only contribution is the cost disclosure ($0.04 USD estimated, usage-based, account-specific) — genuinely useful and not present in the annotations — but it says nothing about result volume, latency, or what 'broad match' actually returns.

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 text is short, which is superficially good, but it is short because it omits the essential content rather than because it is efficient. The markup comments and repeated price hedging ('not a fixed price', 'may differ') consume the entire budget that should have described 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?

An output schema exists, so return values need not be explained, but that does not excuse the total absence of purpose, usage, and parameter meaning for a two-parameter tool. As written, an agent has no basis for choosing or correctly invoking this tool other than its name.

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?

Schema description coverage is 0% and the description supplies no information about either parameter. The required 'phrase' argument and the 'database' argument (its allowed values, e.g. which Semrush regional/global databases are valid) are completely undocumented in both places, which is exactly the case where the description must compensate.

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 never states what the tool does — not a verb, not a resource, not even the word 'keyword'. It consists solely of a pricing/billing block wrapped in HTML comments, so an agent cannot tell from the description that this retrieves Semrush broad-match keyword data, nor how it differs from siblings like get_semrush_question_keywords or get_semrush_keyword_overview.

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 no when-to-use, when-not-to-use, or alternative-selection guidance of any kind. With ~55 sibling keyword tools available, the absence of any routing hint leaves selection entirely to name-guessing.

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