hcl_console_exec

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

Annotations already cover the safety profile (destructiveHint=true, idempotentHint=false, openWorldHint=false), yet the description adds real substance: it executes exactly one line, it is gated, and pre-existing console output is drained and returned separately as discarded_stale_bytes so stale text cannot be misread as the response. That stale-output disclosure is precisely the kind of behavior an annotation cannot express.

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 core action is front-loaded in sentence one, followed by endpoint selection and then the stale-byte caveat, in roughly 65 words with no filler. The unexplained '(gated)' parenthetical and the dense final sentence cost it a point.

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?

An output schema exists, so return values need not be spelled out, and the destructive annotation covers the risk profile. But for an agent that will push arbitrary console lines to live devices, the definition omits what '(gated)' requires, what 'expect' does (timeout on a regex, presumably), and what happens on failure or timeout — key gaps given the schema is otherwise silent.

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 carry the parameter burden and it only partially does: it documents pipe with concrete formats (`\\.\pipe\<topology>-device<N>` and `telnet://127.0.0.1:<30001..31024>`) and the topology+device pairing with its default endpoint. Two of five parameters are left unspecified — 'expect' is never mentioned anywhere and its semantics are undetectable, and 'command' is only implied by the tool name.

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 names a specific verb and resource — send one line to a device console — plus the transport (HCL's telnet bridge), and the scope limit 'one line' is genuinely distinguishing. It never names a sibling (e.g. hcl_bridge_status for checking bridge health without executing), so it falls short of full sibling differentiation.

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 specifies how to choose between two invocation modes (pipe alone, or topology + device), which is a form of usage guidance, but it never states when to use this tool rather than hcl_verify_connectivity, hcl_bridge_status, or a config-generation tool. The lone hint is the unexplained '(gated)' marker, which implies a precondition without saying what it is.

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