rca_graph_markov_blanket

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses the return format (JSON with parents, children, co_parents, full_blanket), the not_found error behavior for missing node/graph, and the requirement that the node must exist. This gives the agent a clear model of what will happen when the tool is invoked.

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 tightly organized: definition first, then practical use case, then args and return behavior. Every sentence adds useful signal, and the core meaning is front-loaded so an agent can quickly decide whether to invoke it.

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 read-only graph query, the description covers what the tool computes, why/when to use it, what inputs matter, what the output looks like, and the error case. The schema covers the remaining auth/namespace parameters, so nothing an agent needs to call this correctly 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?

The Args section adds actionable meaning for graph_id and node ('the graph to search', 'must exist in the graph; check with rca_graph_get') beyond their schema descriptions. Token and client_id are not elaborated in the description, but the schema already documents their purpose, and the description compensates well for the reported low coverage of the main operational parameters.

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 names a specific verb ('Return'), a concrete resource ('the Markov blanket of a node'), and exactly defines the result as 'parents ∪ children ∪ co-parents'. It clearly distinguishes itself from whole-graph reasoning and other RCA graph tools by emphasizing the minimal node set for one incident node.

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 tells the agent when to use this tool: to scope an investigation to relevant metrics for one incident node before targeted analysis or data pulling. It also advises checking with rca_graph_get if the node may not exist, but it does not name explicit alternatives or give a 'do not use' condition, so there is a small gap in exclusion guidance.

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