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

Annotations already flag destructiveHint and idempotentHint, and the description reinforces this with the crucial consequence that omission from the list revokes access and that an empty list removes everyone. It adds the admin requirement, the workspace-guest validation rule, and the return value — real context beyond the structured fields.

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?

One front-loaded sentence: the destructive replace semantics lead, followed by the prerequisite and constraint. No filler, and the parenthetical about the empty list is placed exactly where it prevents a costly mistake.

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 two-parameter destructive mutation with no output schema, the description covers semantics, prerequisites, authorization, validation constraints, and the return value. An agent could call this correctly without inspecting anything else.

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 baseline is 3; the description earns extra by explaining that userIds is a full replacement set and that an empty array revokes all access — meaning the schema's 'every guest who should have access' does not convey on its own.

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 (REPLACE) and resource (the set of guests who may read a project), and defines the exact semantics — the list is the complete desired state, not an addition. This distinguishes it from list_project_guests and from any implicit add/remove alternative.

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?

Explicitly instructs the agent to call list_project_guests first and derive the new set from it, and names the precondition that every id must be a guest of this workspace plus the admin-only restriction. Both when-to-use and the required prerequisite sequence are spelled out.

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