suggest_command

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

With no annotations, the description carries the whole safety burden and does address the critical trait: it is read-only and returns commands rather than executing them. It does not say what the returned commands look like (flat strings vs. annotated steps) or whether it depends on configured defaults, which leaves a gap for a tool with no output schema.

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?

Two short sentences with zero filler; the core capability comes first and the non-execution disclaimer immediately follows where it matters most.

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 two-parameter suggestion tool with a fully documented schema, the description adequately conveys intent, scope, and the key side-effect stance. The only missing piece is the shape of the returned command output, which has no output schema to cover it.

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 100% and the schema already explains both 'goal' (with examples) and 'exchange' (with default fallback and enumerated options). The description adds no meaning beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ('suggest the exact perp CLI commands') driven by a natural-language trading goal, and the negation 'Does NOT execute anything' cleanly separates it from execution siblings like trade_execute. It never names an actual sibling (explain_command, trade_preview) to route against, so it stops short of full 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?

Use case is clear: turn a goal into commands for manual review rather than running them. The 'review and run manually' clause implicitly routes write-intent users to trade_execute, but no alternative is named explicitly and no exclusion cases are given.

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