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

Annotations already establish this is a read-only, non-destructive call, so the description doesn't need to defend safety. It does add real behavior context: the tool tolerates a rough one-sentence input and produces a planning artifact rather than code, which sets expectations about output. It stops short of describing output structure or length, a minor gap given no output schema exists.

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 purpose and deliverables are front-loaded in the opening sentence, and each following sentence adds a distinct rule. It runs slightly long, and the final clause ('a better basis for the next question than anything asked cold') is persuasive filler rather than operational content.

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 read-only three-parameter planning tool with no output schema, the description covers what it produces and when to reach for it. The main omission is anything about output size, format, or whether follow-up calls (e.g. get_build_prompt) are the natural next step.

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 100% with enums and per-field descriptions, so the schema carries parameter meaning. The description's only addition is that a rough sentence suffices, reinforcing the idea field's low-friction intent, but it doesn't clarify that platforms/experience are optional or what happens when they're omitted.

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+resource (turn an app idea into a first version) and enumerates exactly what comes back: feature triage, screen list, data model, build order. This clearly separates it from siblings like get_build_prompt or get_starter_template, which are downstream artifacts.

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?

Explicit triggers are given ('whenever someone mentions an app they want to build', 'describes what an app should do in any words'), plus explicit sequencing rules: use before writing code and before asking clarifying questions. That last line is unusual and valuable routing guidance, since it tells the agent to call this instead of interrogating the user first.

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