composed_graph

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

With no annotations, the description carries the behavioral disclosure burden. It does state that the tool reads durable events and lets users label outcomes, conveying both read and write-like behaviors. But it omits side-effect details such as whether labeling modifies durable state permanently, whether confidence_delta alters weights, or whether any action is destructive.

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?

Two sentences deliver a high density of useful information without redundancy. The first sentence establishes the domain and data sources; the second enumerates outputs and labeling options. It could be slightly more structured, but it remains appropriately sized for a nine-parameter multi-action tool.

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 high complexity—seven actions, nine parameters, no output schema, and no annotations—the description is insufficient for safe autonomous invocation. It does not state which parameters are required per action, what responses look like, or whether label actions persist changes. The schema defines parameters, but the tool still lacks a complete operational contract.

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 baseline is 3; the description adds useful semantics on top by mapping actions to their results (recent/already-composed lanes, neighbors, never-composed pairs, bounty-mode lanes) and by listing representative outcome labels. This helps an agent interpret the otherwise terse enum values without fully documenting every parameter relationship.

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 identifies the resource as "ComposedGraph memory topology" and enumerates the concrete operations: reading composition events and members, returning lanes/neighbors/pairs, and labeling outcomes. It is clear in capability, but it does not explicitly differentiate itself from sibling tools like memory_graph or memory_timeline, relying instead on a domain-specific term.

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 through its list of operations—querying composition topology and labeling outcomes—so an agent can infer when it might be relevant. However, it provides no explicit when-to-use guidance, exclusions, or alternatives, and the large sibling list makes such routing guidance more important.

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