begin_design

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

Annotations already declare non-readOnly, idempotent, non-destructive, closed-world. The description adds genuinely new behavior: persistence location under the host project root, registry pinning and hash verification, and the truncated:true receipt fallback after commit. It stops short of error/conflict semantics when the same designId is reused with different decisions.

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?

Front-loaded with the core action, then parameters, then behavior, in four tight sentences with no filler. Slightly dense and packs several distinct behaviors into the trailing sentences.

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?

Covers the essentials for a mutation with no output schema: persistence, idempotency, registry pinning, and receipt truncation. Missing is what a session enables downstream and any failure/conflict behavior, which matters for a stateful creation tool sitting among several design siblings.

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 the description must carry the load. It names designId, profile, operationId and optional decisions, and clarifies profile may be an alias or ref; it also flags decisions as optional. It adds nothing about the nested decisions object's accepted keys/values or the meaning of operationId beyond the schema's string constraints.

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+scope: 'Create a persistent design session under the host project root.' An agent can distinguish it from read-only siblings like get_design_context and apply_design_patch. However, it never names a sibling or explicitly contrasts itself with the other design-lifecycle tools.

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?

Usage is only implied: creating a session is naturally the precursor to patching/validating a design, and the idempotency note hints at safe retries. There is no explicit when-to-use, when-not-to-use, or naming of an alternative tool.

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