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

Annotations already declare readOnly=false, idempotent=true, destructive=false and openWorld=true. The description adds non-obvious context the annotations cannot carry: a $0.01 per-call charge and that failures are free, plus the downstream effect of membership. It omits the auth/connection prerequisite and what happens on partial success.

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 tightly packed sentences with the core effect front-loaded and the cost caveat appended. No restated title, no filler.

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 3-parameter mutation with no output schema, the description covers purpose and cost, but an agent still lacks the connection prerequisite, group identifier format, and whether the operation is atomic across add and remove. These are material for correct invocation.

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?

Only 'person' is documented in the schema (33% coverage), and its id-or-email format is already in the schema. The description's add/remove wording does map onto the two array parameters, but it never specifies whether group entries are ids or names, nor how conflicting add/remove entries are resolved.

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 gives a specific verb+resource pair ('add a person to groups and take them out of others') and clarifies that groups grant apps and teams, so an agent knows the effect. It stops short of naming the nearest siblings (directory_list_groups, directory_update_user) to disambiguate membership reads from writes.

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?

Use is implied by the described effect, but there is no explicit when-to-use, when-not, or alternative (e.g., use directory_list_groups to inspect membership first, or directory_update_user for other profile changes). No prerequisites such as an established directory connection are stated.

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