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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds real substance beyond them: exactly what is destroyed (the loser and its id), what is relocated (properties, edges, mentions, ownership), edge-cleanup behavior (self-loops and exact duplicates dropped), irreversibility, and the write-access requirement.

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-loaded with the core action, then rationale, mechanics, and caveats in a logical order where each sentence adds operational value. It is somewhat long, and the extraction-cap rationale could be trimmed without losing callability, but for a destructive irreversible tool the detail is defensible.

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?

An output schema exists, so return values need not be described. Given the destructive, cross-class-validated nature of the operation, the description covers everything needed to call it safely: preconditions, effects, auth, and post-condition (loser id stops resolving).

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 0%, so the description must carry the load, and it largely does: winner_id is 'the one to keep', loser can be given by loser_id or by loser_name with its resolution rule ('canonical snake_case name, resolved within the winner's class'). The `memory` parameter is never explained, and the precedence/mutual exclusivity of loser_id vs loser_name is left implicit.

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 precise verb+resource ('fold a DUPLICATE object into the object it duplicates, then delete it') with the exact scope of the operation. It is trivially distinguishable from siblings like get_object or resolve_names, which are referenced as part of the workflow.

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 says when to use it ('two objects of the SAME class denote one real thing'), why the situation arises (extraction coins near-duplicates because the known-objects hint is capped at newest rows), names the alternative to verify with (get_object on both), and states an exclusion (refuses a cross-class pair).

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