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

Beyond the readOnlyHint annotation, the description discloses meaningful behavior: matching is by embedding/meaning, only text-bearing objects have embeddings, embeddings are built in the background, and empty results usually mean the source lacks embeddings. This gives the agent realistic expectations for edge cases.

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 three sentences with no filler, and the most important idea—semantic nearest neighbors—is front-loaded. Every sentence contributes either mechanism, use case, or an important limitation.

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?

For a simple read-only tool with three parameters and no output schema, the description fully covers what an agent needs: what it does, how it works, when to use it, and why empty results might occur. The schema covers parameter syntax, so nothing critical is missing.

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 the schema already documents all three parameters. The description adds context around object_id by implying it should be a text-bearing source object, but it does not add new detail about type or limit beyond what the schema states.

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 states a specific operation: finding graph objects closest in meaning to one object via stored embeddings. It clearly distinguishes itself from keyword search by noting it finds related objects 'even when no words match,' and it references the sibling search_graph_objects for context.

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 explicitly suggests using this tool to browse outward from something found by search_graph_objects, giving clear contextual guidance. It does not explicitly list when not to use it, but the usage context is clear enough.

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