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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered structurally. The description adds genuinely non-obvious domain behavior: the last remaining sign-in method is never removable, and each method carries a disconnectable flag plus a reason. It does not name the response fields, but with no output schema the prose covers the return shape adequately.

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 short sentences with no filler, and the key rule (the last way in is never removable) is stated early. Each sentence adds distinct information: contents, the removal invariant, and how to perform the two follow-on actions.

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?

For a zero-parameter read-only tool with no output schema, the description supplies everything an agent needs: the contents of the result, the disconnectability semantics with reasons, the non-removable invariant, and the correct sibling actions for connecting or setting a password. Nothing material 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 zero parameters, so there is nothing parameter-level for the description to clarify; baseline is 4. The prose instead spends its budget on the return payload, which is the right allocation.

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 clearly enumerates what is returned: the sign-in methods on the account, whether each can be disconnected and why not, and which providers are not yet connected. It is specific about the resource even though it never uses an explicit verb like 'list' and doesn't name a sibling for contrast. No sibling in the list overlaps meaningfully with it, so differentiation is implicit rather than stated.

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?

It routes related intents away from this tool: to connect a provider you give the user connectUrl, and to set a password you use request_password_reset. That prevents an agent from assuming this read-only tool can perform those actions. It stops short of an explicit 'use this when the user asks about login options' trigger, and no exclusion or alternative list tool is named.

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