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

The description adds important behavior beyond annotations: it reads the workspace and connected Google accounts and changes nothing in them, but also updates AdCopilot's own bookkeeping (last seen time, verified account details, onboarding stage). This reconciles the `readOnlyHint: false` annotation with the read-oriented nature of the tool and discloses the actual side effect.

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?

The description is front-loaded with the tool's purpose and primary return fields, then covers the special `tools` mode and side effects. It is dense but most sentences carry relevant information; minor redundancy and long clauses keep it from being maximally concise.

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 the output schema, annotations, and complex workspace context, the description is complete: it lists returned data categories, explains the `tools` mode, and discloses the bookkeeping side effect. An agent has enough information to call it correctly for onboarding, auditing, or tool-schema lookup.

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 75%, so the schema already documents most parameters. The description adds useful semantics for `tools` — that it returns only those tools' descriptions and input schemas instead of context — but does not explain `refresh`, `source`, or `task`, which are left to the schema or undocumented.

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 names a specific retrieval tool and enumerates exactly what it returns: connected Google products, Google Ads accounts, business profile, onboarding stage, situation/next_step/playbook/cross_reads, and tools_revision. It also clearly distinguishes the special `tools` mode, where descriptions and input schemas are returned instead of the workspace context. An agent can identify this as the workspace bootstrap/overview tool without opening the 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 gives clear usage contexts: a new conversation, a get-started request, or an account audit. It also implies the `tools` parameter use case for checking current tool descriptions and schemas. It does not explicitly name alternatives or when not to use this tool, but the intended invocation scenarios are well signposted.

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