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

Annotations declare only the coarse profile (not read-only, open-world, not idempotent, non-destructive). The description adds substantive behavior the annotations cannot convey: a cached snapshot from the last 12 hours is returned rather than paying for a new one, the reason is index lag, and retries must reuse the same idempotency_key. That is exactly the credit-spend and dedup context an agent needs before calling.

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?

Three short sentences, front-loaded with the action and the surprising caching rule. Every sentence carries information an agent would otherwise have to guess; there is no 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?

With an output schema present, return values need not be described, and the mutation's cost/caching semantics are covered. The only gap is the missing explicit contrast with get_share_of_voice, which would complete the routing picture.

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 coverage is 50%: domain_id is documented in-schema (including its list_domains provenance), but idempotency_key has only length bounds. The description compensates by explaining that the key must be unique and reused on retry, which is the essential semantic for that undocumented parameter.

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?

Names a specific verb (capture a fresh snapshot) and resource (AI Share of Voice) plus the upstream source (DataForSEO LLM Mentions), so the agent knows exactly what the call produces. It does not explicitly distinguish itself from the sibling get_share_of_voice, leaving the read-vs-refresh distinction to inference.

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?

The 12-hour cache rule gives implicit guidance on when a call is cheap versus costly, and the retry instruction is explicit. However, there is no direct when-to-use-this vs get_share_of_voice guidance, which is the most likely confusion given the sibling tool.

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