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

Annotations already declare readOnlyHint=true and non-destructive, so safety is covered. The description adds genuinely new behavioral context — that this is an internal, UI-driven call rather than an agent-facing one — which is exactly the kind of information annotations cannot express.

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, zero filler, and the critical constraint ('never call this yourself') is placed where it cannot be missed.

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 description gives the one piece of context an agent actually needs — that it should not call this tool. Little else is required for a single-parameter internal endpoint.

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 0%, so the description would need to explain cardId, and it does not. However, there is only one required parameter and its name plus uuid format make its meaning largely self-evident without further prose.

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 states a specific function — restoring the Proposal.biz card's state after a chat reload — which is concrete and distinguishable from siblings like create_proposal or get_profile. It stops short of describing what 'state' means or what is returned, but an agent can tell what the tool is for.

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?

This is the rare case of an explicit exclusion: 'Used only by the Proposal.biz card' and 'Never call this yourself.' No ambiguity remains about whether the agent should invoke it.

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