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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds real behavior: capacity is Mon-Fri weekly capacity minus the user's holidays and the person's own time off, only hours on the user's own projects are counted, utilizationPct is null when capacity is zero, and a Pro plan is required. It stops short of noting ordering, inclusion of people with zero hours, or response shape.

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?

A single front-loaded sentence that lists the returned metrics before the caveats, with no filler. It is dense and parenthesis-heavy, and the clause 'Names are typed by other people' is cryptic without explanation, which keeps it from a 5.

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 must carry the return values, and it does: the per-person fields, the meaning of utilizationPct, and its null case. Gaps remain around which people are included, ordering, and how partial weeks or days without capacity are handled.

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%, so the from/to format is already documented; the description adds the non-obvious constraint that the range may be at most 400 days and that holiday/time-off exclusions affect the computed capacity for that window. That is genuine meaning beyond the schema, though it does not discuss inclusive/exclusive boundaries or timezone handling.

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 enumerates exactly what the report contains per team member: capacity for a range, hours on the user's projects, billable hours, and utilizationPct. That is far more specific than the title, and it implicitly separates this from hour-listing siblings like get_time_report, though it never names an alternative report tool (get_workload, get_billing_report) to contrast with.

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 implied rather than stated: the 400-day range cap tells the agent to keep windows bounded, and 'A Pro feature' signals an entitlement prerequisite. There is no explicit when-to-use versus get_workload or get_time_report, and no statement of what happens outside the range limit.

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