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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds that analysis operates over previously 'recorded dependencies', which is useful context, but says nothing about truncation via max_hops, empty/unknown-node behavior, or what the traversal returns.

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, front-loaded with the resource and the mode taxonomy, then the routing hint. No filler, no restatement of the tool name or title.

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 six params, nested objects, an enum with five branches and no output schema, the description covers mode selection and the write-side sibling but leaves the response shape unexplained. An agent knows what to ask for but not what comes back (paths? scores? ranked nodes?).

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 the baseline is 3; the description earns an extra point by giving the tersely-labeled enum values real meaning ('blast radius', 'highest-value diagnostic checks') and by framing 'do_calculus'/'counterfactual' as simulated interventions, which clarifies the intent behind the `do`/`factual` maps.

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?

Specific verb+resource ('Query the root-cause graph') with an enumerated mapping of every mode to the analytic question it answers (diagnose→upstream sources, intervene→blast radius, experiments→highest-value checks). It also explicitly contrasts itself with the write-side sibling oxyo_causal_record, so an agent can distinguish the two without opening a schema.

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?

'Use to analyze recorded dependencies; call oxyo_causal_record to add new edges' gives a clear usage context and names the alternative tool for the write case. The per-mode phrasings also imply which mode to pick, but there are no explicit exclusions or prerequisites (e.g., empty graph behavior, whether edges must exist first).

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