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

Beyond the readOnly/destructive annotations, it reveals multi-workspace report semantics, the 'unavailable' refusal state, distinct write permission fields, and the instruction to relay access messages without naming scopes. It also adds a security-specific behavior: CRM field values are untrusted content. No statement contradicts 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?

The text is long but every sentence is operational, and it is front-loaded with the core return semantics and 'Call this first.' Conditional behaviors are grouped logically, and the security note about CRM values is placed at the end as a distinct, necessary warning.

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 output schema, the description carries the full burden of explaining response behavior, and it does so thoroughly: return categories, multi-workspace shape, unavailable-workspace failures, writeAccess vs crmAccess handling, and prompt-injection caution. An agent has enough context to invoke it correctly and interpret its result before calling data tools.

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 schema already documents workspaceId at 100% coverage, so the baseline is met. The description adds meaningful operational nuance: workspaceId becomes required when workspaceCount > 1, workspace ids come from `workspaces`, and passing it returns one full report for that workspace. This goes beyond the schema without needing to repeat syntax.

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 opens with a precise list of what the tool returns: the acting member, covered workspaces, scopes, write permission, and permission matrix. This clearly distinguishes it from the sibling data tools as the identity/authorization introspection call, reinforced by 'Call this first.'

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 explicit when-to-use guidance ('Call this first'), conditional parameter guidance ('When authorization.workspaceCount is more than 1... pass workspaceId'), and stop-conditions for downstream tools ('When crmAccess.allowed is false, no data tool will run... repeat crmAccess.message instead of retrying'). This is actionable routing behavior, not just a general description.

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