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

The line 'Read-only despite being a POST' is genuinely additive: it pre-empts an agent's natural inference that POST implies a mutation, and it is consistent with readOnlyHint=true. The endpoint mapping (POST /v2/permissions.listRoles) adds further context. It stops short of describing pagination or return behavior, but the safety profile is clear.

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?

Two short sentences with the core purpose front-loaded and no filler. The POST/read-only caveat and endpoint reference are compressed into a single clause each, so every element earns its place.

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?

For a read-only list tool with no output schema or required parameters, the description covers the essentials: what it lists, its scope (workspace), and its safety profile. Only return shape and pagination expectations are unaddressed, which is acceptable given the schema documents the cursor contract.

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 limit, cursor, and search are already documented in the schema, including their ranges and pagination semantics. The description adds nothing beyond that, which is the expected baseline when the schema carries the full parameter burden.

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 ('List the roles defined in the workspace'), which is unambiguous about what the tool returns. It does not, however, differentiate itself from adjacent siblings like unkey_list_permissions or unkey_list_identities, so an agent must infer the boundary between roles and permissions.

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?

The description gives no when-to-use, when-not-to-use, or alternative routing guidance. Nothing tells the agent whether roles are the same as permissions or which sibling to pick when the desired object is ambiguous.

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