steps

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered structurally. The description adds one genuinely new behavioral fact — 'the exit code is the verdict' — signalling that the result is judged by an exit code, but it never explains what that code means or what the plan output contains.

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 tight sentences with no filler, and the core scope statement is front-loaded. 'To its return point' is terse to the point of being obscure, but nothing is wasted.

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?

With no output schema and four parameters influencing the result (tier scaffolding, change profile, runtime resolution), the description should explain what a 'step' looks like and how the exit-code verdict is reported. Instead the agent is left to guess at the return shape and the meaning of 'return point'.

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%, so path, tier, change, and runtime are already documented in the schema, and the description does not elaborate on any of them. The baseline of 3 applies; 'for one file' only loosely restates the path parameter.

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 identifies the resource produced — an ordered implementation plan for one file — which is more specific than the bare name 'steps'. However it is a noun phrase with no explicit verb (generate? fetch? derive?) and gives no signal distinguishing it from siblings like route, mind_plan, or gate, so an agent must infer the operation.

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?

There is no statement of when to use this versus alternatives such as mind_plan, route, or gate, and no prerequisites or exclusions. The phrase 'to its return point' hints at scope but does not tell the agent under what conditions this tool is the right choice.

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