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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful non-schema context — that the result is session-scoped and may include an acting-as override — but it does not explain what an acting-as override implies or what calling this changes (it changes nothing, which is worth stating).

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, tightly written, with the return contents front-loaded and the usage instruction trailing. Every clause carries information and nothing is padded.

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?

With no parameters and no output schema, the description carries the whole burden of describing what comes back, and it does so in prose (business, user, acting-as state). There is no missing prerequisite or return-shape ambiguity for an agent.

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?

The tool takes zero parameters, so the baseline of 4 applies. There is nothing for the description to disambiguate beyond the fact that the call requires no arguments.

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 precise verb and three distinct return subjects (current business, current user, acting-as override state) scoped to 'this MCP session'. An agent can distinguish it immediately from siblings like list_businesses or switch_business, which enumerate or mutate businesses rather than report context.

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?

It states an explicit triggering condition: 'Use before any destructive action.' That is concrete guidance. It falls short of 5 because it never names the alternative it complements (switch_business, apply_structure) or contrasts when to read context versus switch it.

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