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

Annotations only declare write/safety flags; the description adds substantive behavior: optional document (starts empty without one), a hard limit of 3 non-home dashboards, plan gating with named error codes (PLAN_REQUIRED, DASHBOARD_LIMIT_REACHED), and that validation errors name the offending path and allowed values. This is genuine value beyond the structured hints.

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 and mostly information-dense, with no filler sentences. The middle clause chain (size/style/scene/density) is semicolon-heavy and reads as a run-on, which slightly hurts scannability.

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 creation tool with a rich nested schema and an output schema, the description covers the pieces an agent needs: empty-start behavior, plan/limit failure modes with exact error codes, validation error shape, and the follow-up path. Nothing essential 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% and enum lists already live in the schema, but the description adds meaning the schema cannot: that size 'auto' is a computed default derived from the widgets, that style overrides card color/icon from tiles.icons, that scene comes from update_topic, and that theme.density compact tightens tiles. That lifts it above the baseline 3.

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 and resource ('Creates a dashboard besides home') and immediately scopes it against the built-in home dashboard and against update_dashboard for adding cards. An agent can distinguish it from archive_dashboard/list_dashboards/update_dashboard without reading schemas.

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 routes follow-up work to update_dashboard ('Add cards afterwards with update_dashboard') and points to get_capabilities (tiles.draws) for widget/type constraints, plus a design norm ('one dashboard per theme'). No explicit when-not-to-use beyond plan gating, so it stops just short of the top band.

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