basecoat_compose_stack

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

Annotations already declare readOnlyHint/idempotentHint=true and destructiveHint=false, establishing this as a safe, repeatable composition step with no persistence. The description adds value beyond that by naming the produced artifact (a full shell architecture with hydrated slots), the downstream verification step, and the optical density concept; it still says nothing about the returned payload, but with annotations covering the safety profile and no output schema, this is a solid disclosure.

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 sentences, both earning their place: the first front-loads the stage and the core action, the second routes to the next tool. The long parenthetical stack enumerations and bracket tag make it dense, but they carry real routing information rather than filler.

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 10-parameter, zero-required composition tool with full schema coverage and no output schema, the description supplies the missing conceptual layer: what a 'shell + stacks' composition is and how it is validated afterward. The omission of return-value/pagination-style detail is acceptable precisely because no output schema exists to be redundant with, though a hint about the returned artifact would close the gap.

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 every parameter (including the alias cluster id/name/shell/componentId, the stacks array, and density) is already documented with defaults and enums in the schema. The description's examples overlap heavily with the schema's own examples for `stacks`, adding little new syntax or format meaning. Baseline 3 applies when the schema carries the load.

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 names a specific verb+resource ('Assemble full shell architectures', 'hydrate pre-configured component stacks into slots') and enumerates the concrete artifacts involved (sidebar-01..16, topbar-shell, kpi-4-col-delta, data-table-full-crud). It is clearly distinguishable from siblings like basecoat_component_syntax or basecoat_quality_inspector, including by nominating one of them as the follow-up stage.

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?

The '[STAGE 3: SYNTAX & STACKS]' prefix and 'Next step: Call basecoat_quality_inspector to verify markup compliance' give explicit workflow sequencing, so the agent knows where this fits. However, it never states when NOT to use it or which sibling covers the adjacent stages (e.g., basecoat_page_architect), leaving the only exclusion to inference.

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