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

With no annotations, the description carries the full behavioral burden and mostly doesn't. It never states whether the calculation is pooled-SD or Glass's delta, what happens when the groups have different lengths, whether the result is a single number, or that the operation is a pure read with no side effects.

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 padding, with the core purpose front-loaded before the input hint. Efficient, though the second clause slightly duplicates the first by re-explaining what Cohen's d measures.

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 stateless statistical calculation with no output schema, the description should at minimum say what comes back (a scalar d value) and clarify the two unexplained parameters. It covers the concept adequately but leaves return shape and half the inputs to inference.

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 nominally 100%, but the schema descriptions are vacuous placeholders ('A to process', 'Group1 to process'), so no real meaning is conveyed. The description names group1/group2 but calls them 'arrays' while the schema types them as strings, and it never mentions the a/b parameters at all — leaving half the inputs unexplained.

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 names a specific verb and resource ('Calculate Cohen's d effect size between two groups') and even glosses the meaning ('how far two means differ in standard deviations'). It does not differentiate from near-neighbors such as x402-effect-size or x402-odds-ratio, which the agent cannot distinguish without opening schemas, so it stops short of a 5.

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?

It says to 'provide group1 and group2 arrays' but gives no when-to-use condition, no prerequisites (e.g. minimum sample size, equal-length groups), and no pointer to alternative effect-size tools. An agent gets no routing guidance at all.

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