Guardrail change history

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

Annotations already declare read-only/idempotent/non-destructive, and the description goes well beyond them: ordering, page-size bounds and default, the cursor mechanic, and a full enumeration of what each revision contains including the semantics of restore_body. That is exactly the kind of context annotations cannot supply.

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?

Three compact clauses lead with purpose, then pagination, then payload, then applicability. Every sentence carries information; nothing restates the title or the annotations.

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, but the description compensates by enumerating each returned field, including expected enum values for source. For a 3-parameter read tool with rich annotations, an agent has everything needed to call it and interpret the result.

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 baseline is 3; the description adds real value by tying limit/before to a coherent pagination story ('limit 1 to 50, default 20; before for the next page') and by naming the fields returned. Minor gap: no format example for the cursor value beyond the schema's 'next_before'.

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?

States a specific verb and resource ('Lists an account's guardrail revisions') plus ordering ('newest first'), which separates it cleanly from siblings like list_events, list_account_settings, and get_account_settings. An agent can identify it 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?

Explicitly gives the triggering conditions: the user asks what changed, who changed it, or wants to restore an earlier rule set. It does not explicitly name the write-side alternative (update_account_settings / revert_account_settings_batch) that would consume restore_body, so the routing is clear but not fully closed.

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