ai_deploy_proxy

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

No annotations are provided, so the description must carry the full behavioral burden. It does disclose useful traits: 'AI keys go only to server-side secrets' and 'LIVE side effects: human approval.' However, it omits critical operational detail: what the human-approval workflow looks like, how approval_id is obtained, what gets mutated (functions, migrations, secrets, auth), and whether deployment is reversible. For a live-effect deploy tool with zero annotations, this is partial transparency.

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?

Three compact sentences with no filler. The key live-effect warning is placed last, which is a reasonable emphasis, though the conditional 'this is backend_deploy' framing makes the first sentence harder to parse than necessary.

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?

Although an output schema exists, the tool has a live-effect deploy with human approval, four undocumented parameters, and no annotations. The description leaves the approval flow, parameter meanings, and override behavior under-specified. Given the complexity and risk, this is insufficient.

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 all four parameters (app_dir, project_ref, approval_id, daily_limit) are undocumented in both schema and description. The description hints at approvals ('human approval') but does not explain approval_id, does not define project_ref or app_dir, and does not mention daily_limit at all, which is a meaningful limitation knob. The description does not compensate for the coverage gap.

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 names a specific action ('Deploy the AI backend') but then immediately complicates it by saying 'this is backend_deploy' in one mode and 'legacy ai-proxy deploy' in another. It is not clear whether ai_deploy_proxy is its own tool, an alias for backend_deploy, or a mode switch. The sibling list contains both backend_deploy and ai_configure, making the distinction ambiguous.

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 gives a mode-dependent condition ('with app.spec.json in subscription mode this is backend_deploy... credits mode keeps the legacy ai-proxy deploy'), which implies when each behavior applies. However, it does not tell the agent when to call ai_deploy_proxy versus calling backend_deploy directly, nor what prerequisites besides app.spec.json are needed. Usage is implied rather than explicit.

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