COA Deploy

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

The description adds behavioral context beyond annotations: it explicitly warns 'DESTRUCTIVE: modifies the deployed environment' (matching destructiveHint=true), details the confirmation requirement ('confirmed must be true to execute'), and clarifies the validation scope ('Does NOT re-validate project contents — validates the plan structure only'). This is valuable additional transparency. A minor gap: it doesn't mention whether the operation is synchronous or async, but the return format suggests synchronous. Still, strong.

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 well-structured: a concise purpose sentence, a warning line, prerequisites, then a clear 'Args' list, and a 'Returns' line. It is efficient but slightly redundant with the schema (the Args list largely mirrors the schema properties). However, the structure aids quick comprehension. Minor redundancy prevents a 5.

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?

Given the tool's complexity (destructive, confirmation requirement, plan prerequisite, return format), the description covers all essential aspects: purpose, behavioral traits, prerequisites, argument details, and return schema. The presence of an output schema reduces the burden, but the description still provides complete context for safe and correct invocation.

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?

With 100% schema coverage, the description still adds significant meaning: it re-explains each parameter in a clear 'Args' list, emphasizing the critical points (e.g., 'plan: path to coa-plan.json', 'confirmed: must be true to execute'). It goes beyond the schema by grouping optional parameters and explaining the 'profile, token' fallback behavior. This fully compensates for any dependency on schema.

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 'Apply a plan JSON to a cloud environment. Changes environment schema/state.' This is a specific verb+resource combination that distinguishes the tool from siblings like coa_plan (which produces the plan) and coa_run (which runs a pipeline). The purpose is unambiguous.

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 description provides explicit usage guidance: 'The plan file must exist (produced by coa_plan). Does NOT re-validate project contents — validates the plan structure only.' and 'Requires confirmed=true.' It clearly indicates when to use (after coa_plan) and the needed confirmation. While it implies not to use without a plan, it could explicitly name the alternative (coa_plan) for when-to-use differentiation, but the guidance is strong.

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