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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly states that this is a deletion operation and notes that it returns a deletion confirmation. It does not mention irreversibility, whether the linked nodes are preserved, or any authorization requirements — gaps that matter for a destructive tool with zero annotation coverage.

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 compact and well-structured: a one-sentence purpose, an Args list, and a Returns line. Every part earns its place, and the primary action is front-loaded. No filler or redundant elaboration.

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 covers all four parameters and the return type, and the usage fallback logic is reasonably complete. However, it leaves ambiguity about whether relation_type is truly optional when identifying by source+target (which could affect uniqueness), and it does not state the side-effect scope — specifically whether deleting a link leaves the associated nodes intact. For a destructive tool with no annotations, this is a meaningful gap.

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, and it does. It explains the role of each parameter and the precedence relationship: id takes priority, and source_id/target_id/relation_type are the fallback keys when id is absent. This adds real meaning beyond the bare schema properties.

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 opens with a specific verb and resource: 'Elimina un enlace del grafo de memoria' (deletes a link from the memory graph). This clearly distinguishes the operation from broader tools like delete_hipocampo or graph_hipocampo, though it does not explicitly name those siblings.

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 Args section provides conditional routing logic: use 'id' if known; otherwise delete by source_id + target_id + relation_type, with target_id marked as required when id is absent. This tells an agent how to select between two invocation patterns. It does not, however, explain when to choose unlink_hipocampo over delete_hipocampo or other sibling tools.

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