read_graph

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

With no annotations provided, the description carries the full burden of disclosing behavior. It reveals the important trait that the entire graph is loaded into memory and may be large, which is critical for performance considerations. It also clarifies the return contents. This goes beyond a simple 'read' statement, though it doesn't cover every possible behavioral facet.

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 extremely concise: two sentences that front-load the purpose, specify returns, and add a critical note about memory. Every sentence earns its place with no fluff or redundancy.

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 no-parameter read tool with an output schema, the description is fully complete. It explains what is returned and warns about the memory footprint, which is the primary caveat. The existence of an output schema covers return-value details, and siblings provide alternatives for more targeted operations.

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?

The tool has zero parameters, making parameter semantics trivially complete. The baseline for no parameters is 4, and since there is nothing to clarify, the description need not add extra information.

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 'Read the entire knowledge graph' with a specific verb and resource, and further specifies it returns 'all entities with observations and all relations.' It distinguishes itself from siblings like search_nodes and traverse by indicating it reads everything at once.

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 implies usage for full-graph access and warns that it loads the full graph into memory, which may be large. However, it never explicitly mentions alternative tools for partial queries or gives when-to-use/when-not-to-use guidance, leaving the agent to infer when this tool is appropriate.

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