update_graph

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

With no annotations provided, the description carries the full behavioral burden. It discloses the critical traits: PUT semantics and 'сырой replace без бэкапа' (raw replace without backup), which warns the agent that existing content is overwritten and irreversible. It doesn't cover auth requirements, rate limits, or return behavior, but the most decision-relevant behavior is stated.

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 front-loaded clause gives the operation and its main distinction from edit_graph_live; the second half folds the input-format guidance into one compact passage. Slightly dense but every clause earns its place.

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 destructive 7-param mutation tool with no annotations and no output schema, the description covers the essential scope, the destructiveness warning, and the accepted payload modes. It stops short of documenting the remaining parameters (graphId requiredness, canvasMeta, name), so it isn't fully complete, but the decision-critical context is present.

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 description coverage is only 14%, so the description must compensate and does: it explains that graphFile takes a local file path (and explicitly says the graph need not be sent inline — convenient for large graphs), and that a graph-container or raw nodes/edges are accepted. That meaningfully clarifies the two input modes, though it doesn't fully document all 7 parameters (name, canvasMeta, graphId are left silent).

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 states a clear verb and resource ('Залить узлы/рёбра в граф' — upload nodes/edges into the graph) and explicitly distinguishes the tool from the sibling edit_graph_live, which it says is for editing existing/live scenarios. This is precise and disambiguating.

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?

It explicitly names the alternative (edit_graph_live) and the condition that selects it — use that tool for editing an EXISTING/live scenario, implying this one for full replace. It also tells the agent which input formats are acceptable in preference order.

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