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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: per-caller visibility ('a staff member sees only their own') and the meaning of truncated: true plus the obligation to report incompleteness. It does not explain ordering, volume, or whether entries include deactivated/revoked connections.

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?

Front-loaded and short in absolute terms, but the middle run of flag definitions is dense and hard to parse — 'elsewhere' is explained with nested parentheticals ('another person's then shows no dates'). Flag names are crammed into prose instead of being separated or marked as return fields.

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 input parameters and no output schema, the description carries the full load and mostly does: it covers caller scoping, completeness signaling, and the three relationship flags. The gap is that the return shape itself (list of app objects with fields) is never explicitly framed, so the flag discussion reads as undefined terminology on first pass.

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?

With zero parameters there is no parameter semantics to add, so the baseline would be 4. However, the description spends its text defining output flags (allBusinesses/elsewhere/yours/truncated) without ever stating that these are fields on returned records, leaving the reader to infer that from context given there is no output 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 and resource up front: the full set of AI apps connected to this business, plus the per-item payload (who connected it, when, last used). It is clearly distinguishable from mutation siblings like disconnect_agent, though it never names a sibling or an adjacent list tool to route against.

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?

Usage is only implied — read the list to audit connected apps. There is no explicit when-to-use/when-not guidance and no mention of the natural alternative (disconnect_agent) or any prerequisite. The one operational instruction, telling the reader to disclose truncation, is present but is about output handling, not tool selection.

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