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 mutation profile is covered. The description adds real context the annotations don't: the 49-item bulk ceiling, the authorization model (root vs. session-bound agent), and the fact that no on-chain transaction is emitted. What it doesn't say is what state is destroyed for the removed wallet or whether unlinking is reversible.

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?

Four short sentences, front-loaded with the action, then permission tiers, then the on-chain clarification. No filler, no repetition of the schema's constraints as prose.

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 no explanation, and the description covers action, permissions, bulk limit, and chain behavior — enough to call correctly. The remaining gap is post-conditions: what the unlinked address loses and whether the removal is reversible, which matters for a destructive tool.

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 description coverage is 100%, so the schema already documents targetAddresses and idempotencyKey semantics, establishing the baseline of 3. The description does add one useful constraint beyond the schema — that non-root callers must pass a single address matching the session wallet — but the bulk permission mapping is already implied by maxItems=49.

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 and resource ('Remove wallet(s) from protocol identity membership') and immediately scopes it against the sibling link tools (generate_link_code, approve_link_consents, submit_link_consent) by describing unlinking rather than linking. An agent can distinguish unlink from link operations without opening a schema.

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 selection rules: root bound wallet may bulk-unlink children, while a non-root linked agent must pass exactly one address matching the session wallet. It also clarifies that no on-chain unlinkAddress transaction is involved, which implicitly points away from an on-chain alternative. It stops short of naming a specific sibling tool to use instead when the caller lacks permission.

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