list_roles

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

No annotations are supplied, so the description carries the full burden. It reveals that roles come from the account's SSO portal, implying an external/auth-dependent lookup, but says nothing about caching, whether stale results can be returned, what force_refresh does, or what failure looks like — gaps that matter given a sibling cache_status and a force_refresh parameter.

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?

A single front-loaded sentence with no filler or repetition. It is efficient, though the brevity is partly the cause of the semantic gaps scored elsewhere rather than a model of completeness.

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?

Output values need not be explained because an output schema exists, but for an auth-dependent, cacheable lookup with an undocumented org selector and a cache-control flag, the description is too thin. An agent could call it but cannot reason about auth prerequisites, caching effects, or how org selection interacts with account_id.

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 0% across three parameters. The description implies account_id ('on one account') but gives no meaning for 'org' (nullable, defaults to null) or 'force_refresh' (boolean, defaults false), leaving two of three parameters undocumented in both schema and description.

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?

Specific verb plus resource plus scope: 'List the IAM roles granted to you on one account, via that account's SSO portal.' An agent immediately knows this returns the caller's own role grants for a single account, which separates it from explain_role_selection or refresh_accounts. It stops short of explicitly contrasting with any sibling by name.

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?

There is no when-to-use or when-not-to-use statement and no named alternative. The phrase 'granted to you' and 'SSO portal' hint at the precondition of being logged in, but an agent is left to infer when to call this versus explain_role_selection, refresh_accounts, or cache_status.

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