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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add domain behavior. It does: it enumerates the returned metrics and explains the non-obvious property that retention and turnover need not sum to 100%. Slightly reduced because an output schema exists, making the return-value enumeration partially redundant.

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 sentences, no filler, and the differentiating mechanism is front-loaded ahead of the alternative routing. Every sentence carries a distinct job: what it does, when to use it, what to use instead.

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 4-param pure-calculation tool with a full output schema and complete annotations, the description covers purpose, routing, and the key conceptual subtlety. Minor gap: it does not reinforce the schema constraints (leavers cannot exceed the corresponding headcount/new-hire totals), though the schema states them.

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 100% and each parameter is documented in the schema, so the baseline is 3. The description still adds conceptual meaning beyond the schema by explaining why the leaver count is split into two inputs, which helps an agent populate them correctly rather than guessing at a single total.

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 and resource ('Calculate the employee retention rate exactly') and immediately pins down the defining mechanism: separating leavers from the starting group vs. leavers hired during the period. It names the sibling employee_turnover_rate and the condition that distinguishes the two, so an agent can route without opening either schema.

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?

Explicit when-to-use ('when you can tell those two groups of leavers apart') paired with an explicit when-not plus named alternative ('Use employee_turnover_rate instead when you only have one total for people who left'). This is textbook alternative routing.

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