Restore Entity

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

With zero annotations, the description carries the full burden and succeeds impressively. It discloses mutation ('creates a new model version'), ID preservation, tombstone resurrection mechanics, un-orphaning of controls, reachability verdict flips for trust_boundary, and the re-attestation requirement for assumptions — exactly the non-obvious side effects an agent needs to anticipate.

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 core purpose is front-loaded in the first sentence, and the per-type effects are organized into scannable bullets. Though long, the length is justified by genuine complexity — five dispatch branches each with distinct semantics — and no sentence is redundant or restates schema content.

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?

The description is unusually complete for a polymorphic mutation tool: it covers preconditions, versioning side effects, per-type outcomes, and downstream consequences like re-attestation and verdict flips. The only gaps are error behavior (what happens if the entity is not soft-deleted, or if entity_type/entity_id is invalid) and server_version semantics — minor omissions given the output schema covers return values.

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 75%, so the schema does most of the work. The description adds substantial meaning beyond the schema by explaining what each entity_type value actually does behaviorally (distinct effects for asset, attacker, component, trust_boundary, assumption) and clarifying that entity_id must reference a soft-deleted entity. However, server_version remains 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?

The opening sentence names a specific verb ('Un-soft-delete'), a precise resource ('a single entity of any core type'), and ties it to its inverse operation ('reversing a prior remove_entity'). It further enumerates the five supported entity types. This fully differentiates it from the large sibling set, especially remove_entity and the various add/edit tools.

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 gives a clear precondition ('Only affects an entity that is currently soft-deleted') and positions the tool as the reversal of remove_entity, which tells the agent when it applies. It does not, however, explicitly name alternatives or state when-not-to-use cases (e.g., that active entities should go through edit_* tools instead), so it falls just short of full routing guidance.

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