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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious context beyond that: the operation is a metadata save with no downstream publishing/scheduling, and results are observational so causal claims are unsupported. It does not disclose duplicate-handling or idempotencyKey behavior, but the annotations cover idempotency.

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 payload, with the two constraints following. Every sentence carries information, though the closing causal-attribution sentence is more of an interpretive directive than a description of the tool's own behavior.

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?

The output schema exists, so return values need no explanation, and annotations cover the safety profile. However, for a 6-required-parameter mutation at 0% schema coverage, the description leaves idempotencyKey, brandId scoping and minimumPostsPerVariant unexplained, which is a real gap for correct invocation.

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% across 7 parameters, so the description must carry the load and it only partially does. It names hypothesis, metric and 'labeled post variants' (hinting at the label/postIds structure), but brandId, idempotencyKey and minimumPostsPerVariant are left completely undocumented in both schema and prose.

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 gives a specific verb+resource ('Save ... an observational content experiment') and enumerates the core payload (hypothesis, success metric, labeled post variants), which lets an agent distinguish it from get_experiment and list_experiments. It stops short of explicitly naming those siblings, so it is clear but not fully differentiated.

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?

'Does not publish or schedule' explicitly carves out the boundary against the many schedule_*/publish-adjacent siblings, and the causal-attribution caveat sets expectations for use. It never names an alternative tool or states a positive when-to-use condition, so it falls short of full routing guidance.

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