Create Visualization

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

Annotations already declare readOnly=false, destructive=false, and idempotent=false, so the mutation profile is largely covered. The description usefully adds that the artifact is created in the library (reusable, not dashboard-scoped) and that `space` defaults to the default space, but it says nothing about permissions, duplicate-title behavior, or where the created object can be found afterward.

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 short sentences: the core action and its dashboard exclusion come first, then the parameter note. Every element earns its place with no 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?

An output schema exists so return values need not be explained, and the nested spec schema is richly documented. However, for a non-idempotent creation tool with a complex required nested object, the description omits any note about permissions, failure modes, or what to do with the created object — leaving gaps the schema cannot cover.

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?

Top-level schema coverage is 0%: the required `spec` object has no description in either the schema or the description, so the description only compensates for the `space` parameter (id targeting, default space). The shape of `spec` is discoverable from its extensive nested field descriptions, but the description itself adds no meaning for the primary required parameter.

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 gives a specific verb+resource ("Create a reusable visualization in the library") and explicitly scopes it away from dashboard placement with "(not on a dashboard)", which meaningfully separates it from add_panel and create_dashboard siblings. It stops short of naming the alternative tools outright.

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 parenthetical "(not on a dashboard)" implies when-not to use this in favor of panel tools, but no explicit when-to-use, prerequisites, or named alternatives are given. Usage is inferable rather than stated.

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