composed_graph

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

With no annotations provided, the description must fully disclose behavior. It indicates read operations and labeling, but does not specify side effects of labeling (e.g., mutability, persistence), authentication needs, rate limits, or whether labeling is destructive. This limits the agent's understanding of consequences.

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 a single long sentence that packs in many details. While it is not overly verbose, it lacks structure (e.g., bullet points or separate sentences for different functionalities), reducing readability.

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 9 parameters, no output schema, and moderate complexity, the description lists return types (e.g., lanes, neighbors) but does not specify the structure or format of the returns. This leaves gaps for an agent relying on full context.

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 coverage is 100%, so parameters are already documented. The description adds context by grouping actions and outcomes, but does not provide additional semantic detail beyond the schema's property descriptions.

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's purpose: 'ComposedGraph memory topology' and lists specific actions (recent, get, memory, neighbors, never_composed, bounty_mode, label) and outcome types, making it distinct from sibling tools like memory or memory_graph.

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?

No explicit guidance on when to use this tool versus alternatives like memory, memory_graph, or search. The description implies usage through the action enum but does not mention when not to use it or provide comparisons.

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