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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the bar is lower. The description adds real value beyond them by decoding the permission tri-state (allowed/partially/forbidden) and noting that each role carries a member count, which shapes how results should be interpreted.

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?

Three short sentences: scope first, then the permission-value glossary, then the read-only constraint. Nothing is padded and the narration is front-loaded on what the tool returns.

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 must hint at the return shape, and it does — roles, their permissions, member counts, plus the encoding of permission values. That covers what an agent needs to consume the result, though it doesn't mention ordering, pagination or whether system/default roles are included.

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?

Only one parameter (workspace_id) with 100% schema description coverage, including its provenance ('из workspace://list'). The description adds nothing about the parameter, which is fine given the schema covers it, so the baseline 3 applies.

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 ('Возвращает роли аккаунта') plus the payload ('с их правами и числом участников на каждой роли'), which immediately separates it from save_workspace_role and delete_workspace_role in the sibling list. An agent can identify it as the read/list tool for workspace roles 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?

Explicitly frames the tool as read-only and says role creation/editing happens in the UI, which steers the agent away from trying to mutate. It does not name the alternatives (save_workspace_role) directly, and the UI-only claim is in slight tension with that sibling existing, so it stops short of a clean 5.

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