update_graph

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states 'PUT, сырой replace без бэкапа' (raw replace without backup), which is a critical destructive trait. It does not mention all side effects (e.g., whether graphId is required or what happens to omitted fields), but the destructive nature is transparent.

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 two sentences, front-loaded with the core action and method, followed by essential caveats and input options. Every sentence adds value with no fluff.

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 tool with 7 parameters, no output schema, and no annotations, the description covers the main purpose, destructive behavior, input alternatives, and sibling distinction. It doesn't explain every parameter or return value, but for a replace operation the key context is present. The absence of output schema lowers the burden, making this fairly complete.

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%, but the description compensates by explaining graphFile in detail ('путь к локальному файлу — НЕ нужно слать граф инлайном, удобно для больших графов') and clarifying that graph-container or nodes/edges are accepted alternatives. This adds meaning beyond the bare schema for the primary parameters, though some (name, canvasMeta) are not explained.

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 explicitly states what the tool does: 'Залить узлы/рёбра в граф' (upload nodes/edges to graph) with 'PUT, сырой replace без бэкапа' (PUT, raw replace without backup). This is a specific verb+resource+method that clearly distinguishes it from the sibling tool edit_graph_live, which is for editing existing/live scenarios.

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 provides explicit guidance on when NOT to use this tool: 'Для правок СУЩЕСТВУЮЩЕГО/живого сценария используй edit_graph_live' (For editing an existing/live scenario, use edit_graph_live). It also clarifies accepted input formats (graphFile, graph container, or nodes/edges), making the usage context clear.

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