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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine context beyond that: output is text, and failure mode is an explicit error on unsupported frameworks rather than a fabricated answer.

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 dense sentences, front-loaded with what the tool produces, followed by the error behavior. No filler or redundancy.

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, the description correctly states the return is text and describes the failure mode. Both parameters are documented at 100% coverage, so nothing an agent needs to call this correctly is missing.

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%, so the baseline is 3. The description adds meaning to platform beyond the schema by explaining that supplying it overrides inference and lifts the unsupported-framework error, which is behavioral semantics the schema does not state.

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 states a specific verb (generate) and resource (architecture plan) and enumerates the concrete outputs: workflow, platform, packages, starter template, architecture documents. This clearly distinguishes it from the retrieval-oriented siblings (get_workflow, get_package, preview_scaffold), which fetch rather than compose a plan.

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 concrete usage condition: it returns an error rather than a guess when the idea needs an unsupported framework unless a platform is supplied. That tells the agent when the tool will fail and how to unblock it, though it never explicitly contrasts itself with siblings like preview_scaffold or resolve_packages.

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