ipsec_sas

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

No annotations are provided, so the description carries the burden. The '[READ]' prefix signals non-mutating behavior, and 'with state' indicates what data is returned. However, it doesn't disclose whether this requires authentication, whether traffic-triggered state is shown, or what 'state' specifically means (active, expired, etc.). The description adds some value but leaves behavioral details unstated.

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 description is compact - two short sections with a one-line summary, a one-line args note. No wasted words. It's front-loaded with the READ intent. Slightly more detail on return content could be added but the structure is efficient.

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 read-only status tool with a single optional parameter and no output schema, the description is reasonably complete. It names the resource (IPsec SAs), the phases (1/2), the data type (state), and the parameter. However, given the large sibling set with similar status tools (gateway_status, interface_status, states_table), more clarity on what distinguishes this output (e.g., tunnel-specific SA details vs general gateway health) would improve completeness.

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 0%, so the description must compensate. The description explains the single 'target' parameter ('Firewall target name from config; omit for the default'), which adds meaning beyond the raw schema that merely shows a nullable string with a null default. For a single simple optional parameter, this is adequate.

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 states this tool reads IPsec security associations (phase-1/phase-2) with state. The verb 'READ' plus the resource 'IPsec security associations' is specific, and it distinguishes from siblings which cover health, gateway, interface, and other network constructs. However, it doesn't explicitly contrast with sibling tools like gateway_status or states_table, so it doesn't get a 5.

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?

The '[READ]' prefix and 'with state' phrasing imply this is a read-only status/introspection tool for IPsec tunnels. The target parameter guidance ('Firewall target name from config; omit for the default') provides clear usage context. However, it doesn't explicitly state when NOT to use it versus alternatives like gateway_status or states_table.

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