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 behavioral disclosure, and it excels. It discloses that results are paginated, that relations are not paginated while memories are, that decay scores require include_scores, and that invalid inputs raise ValueError. It also details the exact return dictionary structure, making behavior predictable.

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 well-structured and front-loaded: purpose first, then return summary, pagination, detailed args, return schema, examples, and errors. It is long but every section earns its place; there is no redundancy or fluff. The use of headings and examples improves scannability and comprehension.

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 tool's complexity (paginated graph reading, multiple parameters, rich output), the description covers all necessary aspects: purpose, parameters, return structure, pagination behavior, error conditions, and examples. The presence of an output schema and this description together fully equip the agent to use the tool correctly without additional assumptions.

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 input schema has zero description coverage (only titles and defaults), so the description's Args section is essential. It explains each parameter's role, allowed values (e.g., status filter values), constraints (limit 1-10,000, page_size max 100), and defaults. It also provides concrete examples that illustrate parameter usage, adding significant meaning beyond the schema.

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: 'Read the entire knowledge graph of memories and relations.' It clearly distinguishes the tool from siblings like search_memory or cluster_memories by stating its function is to retrieve the complete graph structure, not to filter or analyze. The explanation of return content (memories, relations, statistics) further clarifies its purpose.

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 for when to use the tool: to read the whole graph, with pagination guidance and examples for navigating results. However, it lacks explicit comparison to alternatives such as search_memory or search_unified, so it does not fully reach the 'when not to use' criterion. The pagination advice ('If searching for specific memories or patterns, increment page') is a bit conflated with searching but still offers practical usage direction.

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