graph_link

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

Annotations are minimal (readOnlyHint=false, destructiveHint=false), so the description carries the burden. It reveals that the tool creates edges that affect node viability and triggers review for contradictions. However, it does not disclose potential side effects (e.g., what happens if an edge already exists), whether the operation is reversible, or any prerequisite conditions (e.g., nodes must exist). The description adds some behavioral context but leaves gaps.

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 concise: a single sentence for the core action, followed by a usage explanation, and then a clear argument list. It is front-loaded and avoids unnecessary words. However, the second sentence is somewhat dense and could be broken into shorter sentences for clarity.

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 presence of an output schema (context signal indicates true), the description does not need to explain return values. However, it lacks details about error conditions (e.g., invalid node IDs, duplicate edges) and prerequisites (e.g., nodes must exist). The tool operates in a context of memory modes, which is explained, but operational completeness is moderate.

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 100%, so baseline is 3. The description repeats the parameter list but adds context for the 'rel' parameter by listing it within the use-case narrative. However, it does not provide additional semantics beyond the schema, such as format constraints or examples. The added value is marginal.

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 clearly states the action: 'Add a typed edge between two graph nodes'. It specifies the resource (graph nodes) and the specific use case of connecting authored and compiled memory with relation types like 'contradicts' or 'corroborates'. This distinguishes it from sibling tools like graph_neighbors, which queries connections rather than creating them.

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 provides explicit guidance on when to use the tool: 'Use to connect authored and compiled memory' and explains the effect of different relation types. It mentions the practical consequence that more connections increase node viability and contradictions flag for review. However, it does not explicitly state when not to use it or suggest alternatives, but the context is strong enough for effective selection.

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