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

Annotations declare idempotentHint=true, readOnlyHint=false and destructiveHint=false, so safety is partly covered. The description adds the genuinely non-obvious behavior: this mutates persistent session state that silently changes how all subsequent tools interpret their calls — a real trait beyond the annotations.

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?

Three short sentences, zero filler, and the core state-changing behavior is front-loaded before the persistence note. Every sentence carries distinct information.

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 one required parameter, full schema coverage, no output schema and annotations covering safety, the remaining thing an agent must know — that the effect is session-persistent — is stated. Nothing essential for correct invocation 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 description coverage is 100%, so the parameter is already documented as 'by name or id as list_companies gave it.' The description's 'Takes the company by name or id' repeats that information without adding format, disambiguation, or error-handling semantics. Baseline 3 applies.

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 (point/switch) and the resource it repoints — the connection's active company — and explicitly contrasts it with the sibling that supplies valid values (list_companies). An agent can distinguish this from read/write operation tools without opening any schema.

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 tells the agent when this applies: 'Every tool after it answers about that company until it is switched again,' and names list_companies as the source of acceptable values. No exclusions are given, but no sibling competes for the same job, so this is clear context rather than a gap.

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