List hosts

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

Annotations already cover readOnly/idempotent/openWorld, but the description adds real behavioral context: results are filtered by caller identity, unauthenticated SYSTEM_ACTOR callers bypass the filter, and secrets are never returned (password/password_ref replaced by password_configured). The internal concept tag and 'unchanged from today' changelog phrasing dilute but don't negate that value.

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?

The purpose is correctly front-loaded in the opening sentence, and the redaction detail earns its place. However, the second paragraph leaks internal dev artifacts — a namespaced CONCEPT identifier, 'SYSTEM_ACTOR', and 'unchanged from today' — which are implementation notes rather than agent-facing guidance, so the text is longer than it needs to 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?

With no output schema, the description usefully sketches the return shape (host aliases with password_configured instead of password fields) and the visibility rule that determines the result set. It omits ordering/pagination expectations and what fields an entry otherwise carries, which is a minor gap for a zero-arg list 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?

The tool takes zero parameters, so the baseline is 4; there is nothing the description could add on this dimension and nothing it misrepresents.

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 first sentence gives a specific verb and resource ('List the host aliases') plus the two defining scope qualifiers: entitlement-scoped to the caller and secrets redacted. 'List' vs. the sibling 'tunnel_manager_get_host' / 'add_host' / 'remove_host' is inferable from the verb, but no sibling is named 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?

Usage is implied: reach for this to enumerate hosts the caller can see, and get_host for a single one. The description explains the identity-scoping rule but never states when to prefer this over get_host or over the inventory tools, and gives no exclusions or prerequisites.

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