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

Annotations already declare this a safe, idempotent, closed-world read operation, so the safety burden is covered. The description discloses the return field names, but an output schema exists, so that information is duplicated rather than additive. Nothing about edge cases (e.g. very short times, unit assumptions) or rate behavior is added.

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 tight, front-loaded sentences with no filler. The only mild waste is the explicit 'Returns: {...}' enumeration, which restates fields already present in the output schema.

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 pure two-input calculator, the definition is complete: annotations carry the safety profile, the output schema documents the return shape, and the schema fully documents parameters. Nothing further is needed for an agent to call it correctly.

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% (distance_m and time_minutes are both documented with units and minimums), so the schema carries the parameter burden. The description never mentions the inputs or their units explicitly, adding no meaning beyond what the schema already supplies — the baseline 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 and resource ('Calculate swimming pace per 100m') plus a named secondary output (SWOLF efficiency estimate), which cleanly separates it from the many other pace/sport calculators like calculate_running_pace and calculate_marathon_splits. An agent can identify the domain from the first clause alone.

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 is only implied: a pace calculation obviously applies when you have a distance and a time, which matches the two required params. The only guidance offered is a navigation hint ('See list_bundles for related sport calculators'), which points at discovery rather than telling the agent when to pick this tool over a sibling. No explicit when-not or alternative is named.

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