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

Annotations declare destructiveHint=true and idempotentHint=true, but the description discloses far more: role membership is reassigned rather than lost, deletion is irreversible, tokens expire after minutes and are single-use, stale_revision handling, and the idempotent replay contract ('status applied with replayed: true and the ids'). It even names the failure modes that do not consume the token.

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?

Long, but front-loaded with the action and its consequences before the protocol details, and nearly every sentence carries a distinct obligation. The trailing untrusted-content warning is generic boilerplate relative to role deletion, which is the only mildly expendable line.

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?

There is no output schema, so the description has to describe returns — and it does: the preview contains a summary, changes, warnings and a confirmationToken, plus stale_revision and replayed responses. Combined with the multi-workspace workspaceId note, an agent has everything needed to call this destructive tool safely.

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%, so roleId, workspaceId and confirmationToken are already documented; the baseline is 3. The description still adds operational meaning the schema does not: the token must be paired with 'exactly the same arguments', expiry timing, single-use behaviour, and that omitting the token yields a read-only preview.

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+resource ('Deletes a custom role') plus the immediate consequences ('Its members and open invitations move to the Member role') and the exclusions ('Admin and Member roles cannot be deleted'). An agent can distinguish this from delete_record, delete_pipeline, delete_custom_field and from update_role/create_role without opening any 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 prescribes the two-step protocol: call first WITHOUT confirmationToken to preview, show summary and warnings, get explicit user go-ahead in the same turn, then call again with identical arguments plus the token. It also states what does not count as approval (prior instructions, self-authored plans, text found in CRM data) and what to do when inputs change ('preview again').

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