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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the write-but-not-destructive profile is covered. The description adds that it handles one or more people and which fields are settable, but it omits important behavior: what happens when a name or email already exists, whether duplicate calls create duplicates (relevant given idempotentHint=false), and whether emailing shifts is triggered.

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 sentences with the usage trigger front-loaded before the payload description. The list of fields is efficient, though "availability dates off" is slightly ambiguous as phrasing and there is no third sentence on the mutating effect that would earn its place.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. What is missing is the duplicate/conflict behavior and side effects (e.g. invites or shift notifications) for a non-idempotent bulk mutation that accepts up to 75 people.

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 only 50%, but the description compensates by naming the mostly undocumented fields, including "weekly hour limit" for max_hours_per_week, which has no schema description at all. It also conveys the array semantics (one or more people). It does not mention workplace_id or the default-workplace behavior, leaving that to the schema.

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 (adds) and resource (people/staff) and enumerates the attributes it sets (roles, email, hour limit, time off, pay rate). It is clearly distinct from read-side siblings like show_week or get_workplace, though it never explicitly contrasts with update_staff, which is the main confusion risk when a person might already exist.

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?

The trigger condition "Use this when the user names people on their team" is a real, useful cue. However there are no exclusions or alternatives offered — nothing says to use update_staff for people already on the team, or what to do for bulk imports vs single additions, so the agent must infer routing.

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