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

Annotations already cover the safety profile (readOnlyHint, destructiveHint false, openWorldHint false), so 'Read-only' is redundant. The description does earn credit beyond them by pinning down metric semantics — success rate is computed over finished internships only, plus median survival days and average final score — which prevents misreading the numbers. It omits any note on pagination, result size, or empty-period behavior.

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?

Front-loaded with the metric list, then the read-only note, then the optional filters — a sensible order with almost no filler. The single dense metric clause is long but each item is load-bearing, and the trailing filter sentence is slightly compressed into a fragment.

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?

With no output schema, the description correctly spends its budget defining the returned metrics, which is what an agent needs to interpret the result. What is missing is limited to input conventions — date formats for since/until and how the two person/location filters combine — which is a real but narrow gap for a read-only reporting tool.

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%, so the description must carry the parameter burden and largely does not: it says the filters are optional and names 'mentor_person_id' and 'location_id', but never names since/until explicitly, gives no date format or timezone, and does not describe what happens with an open-ended or inverted period. It only adds optionality, which the schema already conveys via zero required fields.

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 the resource (mentors) and enumerates the exact metrics produced: intern counts, status breakdown, success rate, median days survived, average final score. That is far more specific than restating the title, though it never contrasts itself with sibling reports such as hr_cohort_report or hr_funnel_report, leaving that routing to the agent.

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: an agent can infer this is the report to reach for when the question is about individual mentor performance, and the 'FINISHED internships only' note implies the denominator choice is fixed. There is no explicit when-to-use, when-not-to-use, or named alternative among the many hr_* report siblings.

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