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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behaviour, so the description isn't needed for the safety profile. It adds genuine value beyond them by disclosing the payload shape — title, description, and the role's operating instructions — which matters because no output schema exists, plus an explicit instruction to follow the retrieved instructions.

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 payload contents front-loaded, followed by the behavioural instruction. Minor awkwardness in 'the instructions whoever takes it follows', but nothing extraneous.

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 two-parameter read with full schema coverage and complete annotations, the only thing the description must carry is the return value, and it does — it enumerates the three fields returned. Absent is any mention of what happens if the role name is unknown, but that is a minor gap.

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 coverage is 100%: both 'role' (with a list_roles cross-reference and an example) and 'project_id' (with list_projects cross-reference and default behaviour) are fully documented. The description adds nothing on either parameter, 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?

The description names a specific resource and its returned contents: a single role with its title, description, and the instructions its holder follows. Singular 'One role' implicitly contrasts with the sibling list_roles, but that contrast is never stated outright, keeping it just short of 5.

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 one usage cue — 'If you've been asked to act as this role' — which is really guidance on what to do with the result more than when to call the tool. No alternative is named (the schema mentions list_roles, the description doesn't) and no exclusions or prerequisites are stated, so usage is implied rather than directed.

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