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

Annotations already declare destructiveHint=true and readOnlyHint=false; the description adds the crucial beyond-schema behavior that this is a full-state replacement, not a merge — anything previously granted and omitted is dropped. 'Takes effect within seconds' is a useful propagation note. Minor tension: a full-list replace is arguably idempotent while idempotentHint=false, but the description itself does not assert the opposite.

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?

Three sentences, front-loaded with purpose, then the replacement semantics and the add-a-site recipe, then a propagation note. No restatement of the title and no filler; every sentence carries information an agent would otherwise have to guess.

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?

Outputs are covered by the output schema and nested site shape is fully documented in the input schema, so the description only needs the operational layer — which it largely supplies. The remaining gap is what happens when the email is unknown to the workspace and whether prior grants are validated, which matters for a destructive replace.

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?

With 100% schema coverage the baseline is 3, and the description earns more: it clarifies that 'sites' is the complete desired set (not an increment), that each entry is a folder, app, or domain, and states the 'give this or sites' mutual exclusion with all_sites that the schema itself does not encode.

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 ('Change'), resource ('which sites a visitor may see'), and addressing key ('by their email'), which cleanly separates it from invite_visitor, remove_visitor, and list_visitors. The reader knows it is a per-visitor site-permission mutation, not a workspace-wide settings change.

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?

Gives concrete routing: use list_visitors first, then pass current sites plus the new one to add a site, and use all_sites: true instead of a list. That covers the main alternative and the add-a-site workflow. It says nothing about removing a visitor entirely (remove_visitor) or whether a non-existent email is created, so the when-not side is thin.

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