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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: synchronous execution, task support forbidden, and the presentation contract (assistantSummary first, never expose raw JSON unless asked). It still says nothing about what permissions data is actually returned or any authorization requirements.

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 purpose statement is front-loaded but content-free, followed by three boilerplate classification sentences that largely duplicate annotations, then a long block of response-formatting instructions. The formatting guidance is useful but disproportionately verbose relative to the near-zero information about the tool's actual behavior.

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?

An output schema exists, so return-value structure needn't be explained, but the description leaves the tool's subject matter undefined and completely omits the 15-parameter input surface. For a tool this complex, an agent cannot tell what it queries or how to call it meaningfully.

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?

Fifteen parameters with 0% schema description coverage and zero required fields, and the description mentions none of them. The schema alone gives no semantics for seatId, seatName, accountId, the locale/market fields, or the nested marketContext and marketLanguageProfile objects, so the description had a large burden to fill and contributes nothing.

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?

"get permissions" restates the tool name and title verbatim without naming the resource or scope — seat permissions, user permissions, or account permissions? The description never says what is being retrieved or what distinguishes it from the many sibling get_* tools (get_capabilities, get_current_user, get_current_seat). This is a tautology rather than a purpose statement.

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?

There is no when-to-use guidance and no alternative named. The only contextual instruction is about how to present results (use assistantSummary, avoid raw JSON), which is response formatting, not tool selection. An agent gets no help deciding between this and the other read-only getters.

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