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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds interpretive context (learnings carry a confidence level, supporting evidence, and a validity start point), but that largely restates the output schema rather than disclosing behavior — nothing about freshness, staleness, or cost of the call.

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?

Two sentences, zero filler: the first defines the content and its metadata, the second routes usage. The most load-bearing information (what is returned, and with what qualifiers) is front-loaded.

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 low-complexity, parameterless-required read tool with an output schema and full annotation coverage, the description covers purpose and triggers adequately. The one gap is sibling differentiation among the cluster of get_* insight tools, which is left 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?

Schema description coverage is 100%, including the account-scoping and default-language semantics, so the schema does the heavy lifting. The description only obliquely echoes the 'each ad account' scope and says nothing about the language parameter, so the baseline of 3 applies.

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-resource pair (what Taseli has learned about each ad account) and immediately bounds the content: risks, insights, opportunities, each with confidence, evidence and since-when. The phrase 'from its own results' distinguishes it from sibling insight tools like get_market_insights or get_benchmarks, which draw on external rather than account-specific evidence.

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?

Three concrete trigger phrases ('what did you learn?', 'what works here?', 'what should worry me?') give an agent clear call conditions. It stops short of explicit exclusions — it never says to use get_results for raw performance data or get_memory for stored preferences instead — so routing between the several insight-ish siblings still requires inference.

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