memory_graph

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

With no annotations, the description carries the full burden. It discloses a notable behavioral trait: transitive/inverse edges are pre-derived with 'derived: true' and rule provenance. It also states the return structure. Since it says 'Read', it implies read-only behavior, though it doesn't explicitly mention absence of side effects.

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 and well-structured, with a clear opening sentence, a compact Args section, and a Returns summary. Every sentence contributes useful information without unnecessary verbosity.

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 purpose, most parameters, and return format. The omission of include_facts is a notable gap, but the existence of an output schema mitigates the need for detailed return field explanations. Overall, it provides enough context for an agent to use the tool correctly.

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%, requiring the description to explain parameters. It adequately explains depth, to, and relation_filter, but omits include_facts entirely. The required entity parameter is implicit but not described. This partial coverage leaves a clear gap.

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 tool reads an entity's graph neighborhood, specifying the verb 'Read' and the resource (graph neighborhood). It distinguishes itself from sibling write tools like memory_graph_relate/unrelate by focusing on reading, and the mention of nodes, edges, and facts adds specificity.

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 clear context on what the tool does (reads graph neighborhoods) and offers parameter-specific usage guidance (e.g., 'Pass `to` for the shortest path', 'relation_filter keeps only...'). However, it does not explicitly mention alternatives or exclusions, though the read-only nature implies usage scenarios.

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