run_mcdev_command

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

Goes well beyond the annotations (destructiveHint=true, openWorldHint=true, idempotentHint=false) by naming the specific side effects (overwrite/deletion/auth-persistence), stating that deploy/runtime effects need a user request plus host approval, that no terminal interaction or auto-defaults occur, that diagnostics are bounded projections, and that partial/unknown operations must never be auto-retried. This is exactly the extra context annotations 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?

Purpose and the argv-vs-shell-string distinction are front-loaded, and nearly every sentence carries a distinct operational rule. The style is telegraphic and dense, and the timeout/progress sentence sits at the tail where it is easy to miss.

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 destructive, open-world tool with no output schema, the description covers side effects, consent/approval expectations, retry policy, and the nature of diagnostics. The remaining gaps are the meaning of workspaceRoot and timeoutMs, and where valid command values come from beyond a pointer to mcdev_get_command.

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 coverage is 0%, so the description must carry the load. It does well for args ('exact argv tokens after the canonical command, not a shell string') and partially for command (native mcdev command, consult mcdev_get_command), but workspaceRoot is never explained and timeoutMs is only obliquely referenced by 'Configure host timeouts for long operations' with no units or bounds.

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?

Names a specific verb+resource (execute a native mcdev command) and adds a scoping qualifier ('explicitly requested', 'developer-controlled project'). It distinguishes itself from mcdev_get_command, which it routes syntax lookups to, but never contrasts with the sibling preview_mcdev_project_command, which is the closest alternative for dry-run style invocation.

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?

Explicitly directs syntax/availability questions to mcdev_get_command and states operational rules: 'Supply explicit target/choices; no terminal interaction or automatic defaults' and 'Deploy/runtime effects require the corresponding user request and ordinary host approval.' No explicit when-not-to-use guidance relative to preview_mcdev_project_command, so it stops short of a 5.

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