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

Annotations already declare readOnly, idempotent, and closed-world, so the safety profile is covered. The description adds value beyond that by noting it returns entries plus pagination and is also exposed as structuredContent, and by clarifying that the data is informational only and does not constrain transfers.

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-loads the purpose, then the usage recipe, then the caveat and return shape. The worked example is long but earns its place by disambiguating the resolve-then-confirm workflow; nothing is redundant padding.

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 exists, the description does not need to enumerate return values, yet it still notes pagination and structuredContent. Combined with the workflow guidance and scope caveat, an agent has everything needed to call this correctly.

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 goes slightly further by showing how the 'search' parameter is actually used ('find the entry by name (search)'), tying a schema field to a concrete agent workflow rather than just restating it.

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 (list the saved recipient addresses / address book) and names the fields returned (name, networks, address). It is clearly distinguishable from siblings like transfer_native, wallet_list, and the portfolio_* tools.

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 an explicit triggering scenario ('send 0.1 ETH to My work address'), the exact sub-step (find by name via search, take the address, confirm with the user), and names the downstream tools (transfer_native / transfer_asset). It also states the negative case: 'Informational only: transfers are not restricted to these addresses,' so the agent knows this list is not an allowlist gate.

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