set_object_retention

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

Extraordinarily rich beyond the annotations: no undo token is recorded, S3 refuses to shorten retention without the bypass-governance-retention header which the SDK never sends, COMPLIANCE cannot be lifted by any credential including root until the date passes, and both refusal paths fire under dry_run. This is exactly the destructive/irreversible context an agent needs.

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?

Front-loads the critical [WRITE][risk=critical] warning and 'NO UNDO EXISTS' before the mechanics and args. The prose is dense but almost every clause carries decision-relevant information; only mild redundancy between the header warning and the body costs it a 5.

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?

No output schema exists, yet the description explains what dry_run returns (before-state) and exactly what a refused call does. For a critical, irreversible, 8-parameter mutation tool, nothing needed to call it safely is missing.

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%, so the description carries the full load and does: mode values are explained with their liftability semantics, days is anchored ('from now'), version_id defaults to current, dry_run is defined as running every guard and reporting before-state, bucket_name notes the object-lock prerequisite, and object_name cites its source. All 8 parameters gain meaning.

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: 'Put retention on one object version.' The scope ('one object version') cleanly separates it from set_default_retention, set_legal_hold, and bucket_lock_config. An agent can select 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?

Provides strong conditional guidance: COMPLIANCE requires acknowledge_irreversible=True, shortening/downgrade attempts are refused, and guards still fire under dry_run. It doesn't explicitly compare against sibling tools like set_default_retention or set_legal_hold, so a 4 rather than 5.

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