Compare the results of AI plans

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

The description goes well beyond the readOnly/destructive annotations by explaining key behavioral nuances: ranking is by interactions per MEASURED post rather than totals, only plans with at least 3 measured posts compete, maturing plans have unstable numbers, and missing metrics are not treated as zeros. These are non-obvious behaviors an agent must know to interpret results correctly.

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 description is dense but every clause contributes useful information. It is front-loaded with the core question the tool answers)Skip, then builds logically through ranking, maturity caveat, date filtering, network fairness, and missing metrics. Slightly longer than necessary, but not padded.

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 tool with no output schema and several subtle behavioral rules, the description covers the essential ground: what results contain, how ranking works, when results are comparable, and what missing metrics mean. It does not spell out the exact return shape, but it gives enough high-level context to avoid major misinterpretation.

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 already 75%, but the description adds meaning not present in the schema: date filters apply to the week the plan published in, the sort metric is based on per-measured-post interactions, and social_network should be passed as one value for fair comparisons. It does not discuss pagination parameters, but the schema covers those adequately.

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 opens with a clear, specific purpose: 'Which AI plans worked, and which template works best' and frames the tool as answering 'which of my AI plans did best?'. This clearly separates it from list_ai_plans or get_ai_plan by focusing on comparative results and ranking rather than simple listing or single-plan retrieval.

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?

Usage context is explicitly stated: use it to compare AI plan performance, and important caveats are given, such as only ranked plans competing, maturing plans having moving numbers, and passing a single social_network for fair cross-network comparison. It does not explicitly name sibling alternatives like list_ai_plans or get_ai_plan, so it stops short of full when-not-to-use guidance.

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