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

Goes well past the annotations by disclosing the non-obvious behaviors: partial-update semantics, full-graph replacement (the previous graph is not lost but preserved as a revision), a rollback escape hatch, and a non-blocking `warnings` array in the response that the agent must inspect. Annotations only say it is not read-only/idempotent/destructive; the description adds the real operational 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?

Five sentences, tightly ordered: what it updates, patch semantics, the graph-replacement rule, the rollback path, and the warnings contract. No filler, and the most dangerous constraint (complete graph) is front-loaded near the top.

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 5-parameter mutation tool with a nested graph object and no output schema, the description covers behavior, recovery, and the return-value warning contract well. It stops short of routing between this tool and neuron_toggle_flow for enable/disable, which is the one remaining ambiguity an agent faces.

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, but the description adds semantics the schema does not: that supplying the graph replaces it wholesale and that warnings are emitted only for graph updates. It does not explain the null-clears-description convention (that lives in the schema), so it is slightly above baseline rather than exceptional.

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?

Opens with a specific verb+resource ('Update a flow') and enumerates exactly which fields are mutable (name, description, graph, enabled), which lets an agent distinguish it from neuron_create_flow and neuron_toggle_flow without opening the 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?

Gives clear context: patch semantics ('Only provided fields are changed') and the critical constraint for graph edits ('provide the COMPLETE graph'). It points to neuron_list_flow_revisions and neuron_restore_flow_revision as the recovery path. It does not, however, address when to prefer neuron_toggle_flow over setting `enabled` here, despite the sibling overlap.

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