record_lifecycle

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses that events are written to an action ledger and that decommission requires a disposition, but it does not state whether the ledger is append-only or mutable, whether entries can be corrected or deleted, what permissions are needed, or what the response looks like. For a write operation with zero annotation coverage, this is a significant gap in transparency.

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?

The description is a single, dense sentence that front-loads the verb and resource, enumerates the full event taxonomy, and then adds the disposition condition and regulatory context. Every segment carries meaningful information and there is no filler. The structure is slightly congested — splitting into two sentences would improve scannability — but it remains efficient and readable.

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?

Given the tool complexity (4 parameters, no output schema, no annotations), the description covers the event taxonomy and the disposition relationship, and adds useful regulatory references. However, it does not explain the semantics of `actor` or `note`, does not state whether disposition is required only for decommission or allowed for other events, and does not indicate the return value or acknowledgment behavior. It is adequate but leaves several gaps an agent would need to resolve.

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 must compensate. It does define the allowed values for `event` (the enumerated lifecycle types) and for `disposition` (erased, archived, transferred, retained), and specifies that decommission requires disposition. However, it leaves `actor` (a required parameter) completely undefined — no guidance on who the actor is or what format to use — and `note` is similarly unexplained. The partial compensation is enough for a 3, not more.

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 states a specific action ('Record a lifecycle event') and a specific resource ('action ledger'), and enumerates the exact event types that fall under the tool's scope (start, stop, pause, resume, configuration_change, key_rotation, substantial_modification, decommission). This distinguishes it clearly from sibling record_* tools such as record_incident, record_disclosure, and record_oversight, which handle different categories of entries. The regulatory references (Art. 3(23), Art. 111(2), Annex IV point 6) further disambiguate the purpose.

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?

The description clearly implies the tool should be used when a system lifecycle event occurs, and provides a concrete list of acceptable events. It does not explicitly name alternatives or state 'use X instead for incidents/disclosures/oversight', but the event taxonomy and ledger reference give agents enough context to avoid confusing this with sibling record tools. There is no explicit exclusionary guidance, which would warrant a 5, but the context is clear enough for a 4.

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