patch_graph

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

With no annotations, the description carries full behavioral burden. It discloses that the tool modifies the graph in place, performs string replacements, validates the result, and uploads back with an auto-backup. It also explains preview mode (only count matches, no save) and immediate application of changes. This is thorough and honest about the mutation behavior.

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 dense yet efficient, front-loading the core mechanism and then providing usage guidance and parameter semantics. Every sentence adds value: purpose, when-to-use, replacements behavior, preview mode, and immediate application. No fluff or repetition.

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 mutation tool with no output schema or annotations, the description is quite complete: it explains the operation, parameters, and side effects. However, it does not explicitly state what the tool returns on success (e.g., count of replacements or confirmation), which is a minor gap. Also, there is slight ambiguity about 'active graph' vs graphId, but overall it is sufficient for selection and invocation.

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 50%, but the description strongly compensates by explaining replacements structure {find, replace}, emphasizing all occurrences, and advising specificity of find. It also clarifies graphId's role as the graph identifier. The preview and backup parameters are already described in the schema, so the description adds meaning where needed.

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 clearly states the tool's purpose: patch a large/live graph by applying string replacements server-side without sending the entire graph. It uses a specific verb ('patch') and resource ('graph'), and distinguishes itself from siblings like update_graph and edit_graph_live by explicitly stating it does not transmit the whole graph.

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 says when to use this tool: when the graph is too large to pass whole via update_graph/edit_graph_live. It also provides concrete use cases (changing channel IDs in SUBSCRIBED conditions, button links, texts). Alternatives are named, making the choice clear.

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