List Redmine roles

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

Annotations already declare readOnlyHint/idempotentHint, lowering the bar, yet the description adds substantial context beyond them: the absence of query/include/pagination controls, preservation of Redmine's position order, the id-and-name-only response shape, API-vs-HTML auth asymmetry, and the specific 401/403/404 error behavior with no upstream body exposed. This is exactly the kind of behavioral disclosure that prevents agent confusion.

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 is front-loaded in sentence one, and nearly every sentence carries behavioral value. It is slightly longer than necessary: the note about the HTML roles page being restricted for non-admins only explains the marginal fact that results have no browser links, and the final 'never changes Redmine data' sentence mostly restates readOnlyHint. Overall efficient but not maximally lean.

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 zero-parameter, read-only list tool with an output schema and four safety annotations, the description covers everything needed to invoke it correctly: purpose, endpoint, response scope, ordering, auth requirements, and error behavior. Nothing material is missing for the agent to call this tool successfully.

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?

With 0 parameters, the baseline is 4. The description earns it by explicitly warning that the endpoint 'accepts no query, include, or pagination controls,' which stops an agent from attempting unsupported filters — a real semantic addition given the empty schema offers no such guidance.

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 first sentence states a specific verb ('Read'), a precise resource ('Redmine's non-built-in project-member roles'), and the exact endpoint (GET /roles.json). The scope qualifier 'non-built-in' and the clarification that the list carries only id and name differentiate it from the sibling get_role, which covers the role-detail response.

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 provides clear context: it explicitly notes the list 'does not expose permissions, visibility settings, or other fields from the separate role-detail response,' which implicitly routes an agent needing detail to the get_role sibling. However, it never names the alternative tool explicitly or states a when-to-use/when-not-to-use rule, so it falls short of the top tier.

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