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

Annotations already carry readOnly/non-destructive/non-open-world, and the description goes well beyond them: it discloses that credentials are never returned, explains the egress-IP/ASN type semantics (isp passes, hosting is a datacenter), names installDefault and the no-proxy fallback, and states the one-account-per-proxy sharing risk.

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 operator-only warning and structured as one dense inventory sentence followed by security and safety notes. Every clause carries information, though the long first sentence packs several distinct ideas together.

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?

With no output schema, the description fully carries the return-value burden: it enumerates the returned fields, explains their meaning, and closes the obvious ambiguity (no credentials returned). Nothing needed to call or interpret this tool is missing.

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?

The tool takes no parameters, so per the baseline this is a 4. The description instead spends its effort on output semantics (field meanings, ISP vs hosting classification), which is the right place given an empty input schema.

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?

Specific verb and resource ("Lists the egress proxies an account can be assigned") with concrete detail on what each row contains — label, host:port, vendor-sold country/type, last-check egress IP and ASN classification, consumers, plus installDefault. It distinguishes itself from one-off siblings like li_check_proxy by scope, but never names a sibling explicitly.

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?

"OPERATOR ONLY" sets an access precondition, and it routes the agent away from tools for mutation work (adding a proxy or changing credentials happens on the dashboard, not via a tool). It does not explicitly say when to prefer this over li_check_proxy or how it relates to li_set_account_proxy assignment.

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