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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses non-obvious behavior an agent could not otherwise know: retrying the same request is idempotent and returns the copy it already made, the default naming convention '<source name> (copy)', and the authorization requirement (OAuth or scoped token plus a workspace role that can edit). For a mutation tool this is unusually complete.

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?

Five compact sentences, front-loaded with what gets copied, then what doesn't, then naming, then idempotency, then auth. No restatement of the title or filler, and each clause carries a distinct decision-relevant fact.

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 should ideally say what the copy returns (e.g., the new role id). Idempotency hints at the return value but doesn't define it. Everything else an agent needs to invoke this mutation safely — scope, side effects, naming, auth — is present.

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 only 33% (only workspaceId is documented), so the description has to compensate, and it does: it explains that name is optional, defines the fallback name when omitted, and repeats the 200-character ceiling. roleId is characterized functionally as the source role. It does not add format or resolution guidance for roleId beyond what the schema's UUID pattern already provides.

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 opens with a specific verb and resource ('Copy a role, its description and its criteria into a new role'), and immediately scopes it against the create_role/create_role_from_jd siblings by stating exactly what is and is not carried over (candidates, notes and comments are not copied). An agent can distinguish duplication from fresh creation 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?

Usage context is clear: this is for copying an existing role, and the description clarifies the copy is active even when the source is closed and that the source stays unchanged, which covers the main decision points. It stops short of explicitly naming create_role or create_role_from_jd as the alternative when starting from scratch, so the when-not clause is implied rather than stated.

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