basecoat_page_architect

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds value beyond that by disclosing what is actually returned — scaffolds containing explicit slot markers, grid structures, and responsive containers — which is important behavioral context given there is no output schema. It stops short of describing pagination, size limits, or failure behavior when an id/recipe is not found.

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, front-loaded with the stage label and the core action, followed by the downstream call chain. No filler, though the long parenthetical enumeration of scaffold types is slightly list-heavy and the 'Next step' sentence is compressed enough that its conditional logic is implicit rather than ordered.

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 zero-required-parameter, eight-parameter retrieval tool with no output schema, the description succeeds at conveying both what comes back (slot-marked scaffolds) and where it sits in the multi-step workflow. The main residual gap is that the alias relationship among id/name/block/intent/recipe/componentId is left entirely to the schema, so an agent has no description-level guidance on precedence when several are supplied.

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 all eight parameters are already documented in the schema, including the enums for density and environment. The description supplies concrete example values (workspace-dashboard, auth-split-flow, sidebar-07) that loosely mirror the intent/recipe/block parameters, but adds no meaningful semantics beyond what the schema already states. Baseline 3 applies.

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 pair (search and retrieve) plus the exact resource (complete layout scaffolds) and enumerates concrete artifact types (Workspace Dashboard, Auth Split-Screen, Data Table Detail, etc.). The '[STAGE 1: ARCHITECT]' tag and the emphasis on slot markers/grid structures/responsive containers make it clearly distinguishable from sibling retrieval tools like search_macro_blocks or get_component_html.

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?

Explicitly positions itself as the first stage and prescribes the exact follow-up chain: basecoat_rules_enforcer and basecoat_creative_director, then basecoat_compose_stack or basecoat_component_syntax. This is strong sequencing guidance, but it never states when NOT to use it or how it differs from adjacent retrieval siblings such as search_macro_blocks, get_macro_block, or get_page_architect.

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