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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true, so the safety profile is known. The description adds real behavioral value beyond that: admins authenticate with email+password rather than a Ginta account, they can edit content but never design or code, and add-without-password triggers an invitation email while send_setup_link sends a fresh one. It does not explain the consequences of remove (does access drop immediately?), what set_password does to an existing password, or any rate/repeat limits — with destructive operations present, those gaps keep it at 3.

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?

Front-loaded with the trigger condition, then the behavioral context, then per-action notes — a sensible order with no filler. The per-action clauses are crammed into one run-on paragraph, which makes scanning harder than a short bulleted list would be.

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?

Given an output schema and full annotation coverage, the description supplies what structured fields cannot: who these admins are, how they log in, what they may change, and which action sends email. The main omission is the effect of remove and whether password changes propagate immediately, which matters for a tool flagged destructive.

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, but the description goes further by tying parameters to actions: password is optional on add and means the owner supplied one, email applies to every action except list, and set_password accepts either an admin's address or the owner's own email. That resolves the ambiguity an agent would otherwise face when choosing between add and send_setup_link.

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 identifies the resource (the set of admin users behind /admin) and the operations (list, add, remove, set_password, send_setup_link), and it scopes what those admins can touch — lists, menu, bookings, messages — while explicitly excluding design and code. It never states the purpose in a single crisp opening clause (that lives in the title), and it doesn't name a sibling it is distinct from, so an agent must infer that manage_site/manage_module are different concerns.

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?

Strong triggering guidance: "Use when the owner says who should keep the website up to date" with a concrete example and the situation "after building a site with parts the owner fills in." Each action variant gets its own cue (add with vs. without a password, set_password for an admin or the owner's own email, send_setup_link for a new choose-your-password email). No explicit when-not-to-use or named alternative tool appears.

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