Set Custom Data

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

Annotations only flag readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true; the description adds real value by disclosing that this is a private per-user store and that writes OVERWRITE any existing value at the same namespace and scope — i.e., prior data is silently replaced even though destructiveHint=false. Minor tension: repeated identical writes look idempotent, yet idempotentHint=false. No return-value or error behavior is described, but read-back routing covers the basics.

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 with zero waste: what/where and privacy first, then overwrite semantics and the read-back pointer. Front-loaded and appropriately sized for a 3-param tool.

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?

Given 3 params, one required nested object, and no output schema, the description covers storage location, overwrite behavior, scope partitioning, and how to retrieve the data. It omits anything about size limits, how values are returned, or failure modes, which leaves a small 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% and already documents data, scope, and the canvas-mcp namespace default with examples. The description only reinforces that overwrite is keyed on namespace+scope; it adds no format, depth, or collision guidance beyond the schema.

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 (store) and resource (your own key-value data on your Canvas account) plus the scope qualifier that it is a small private per-user store invisible to others. It cleanly distinguishes itself from its paired sibling get_custom_data.

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 says to read the value back with get_custom_data, and notes namespaces keep data apart from other apps, which tells the agent why the namespace/scope params exist. It does not state when-not to use it (e.g., large blobs vs. files) or any size/serialization limits, so it stops short of full routing guidance.

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