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

Annotations already declare readOnly=false, destructive=true and idempotent=true; the description adds genuinely new context on top: the call is free, and it is a partial merge rather than a wholesale replacement ('nodes or edges not sent keep their stored value'), which materially changes how destructive an agent should treat it. It stops short of saying what happens when the resulting graph is invalid (rejection vs. partial write) or what permissions are needed.

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 dense sentences, front-loaded with the '[write]' marker and the core action, followed by the two constraints that matter most (merge semantics, validity requirement). No filler or repetition of the 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?

For a destructive mutation with no output schema and zero schema documentation, the description covers intent and merge behavior but leaves the agent without the node/edge payload structure or a pointer to get_agent_office_plan for retrieving the current graph before editing. Adequate to recognize the tool, not quite enough to call it confidently.

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 0% and both graph parameters are untyped arrays (items: {}), so the schema explains nothing. The description compensates only partially: it maps name/nodes/edges to their roles and clarifies the merge semantics of omitted arrays, but gives no shape for individual node or edge objects, which the agent cannot guess.

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?

States a specific verb and resource: changes the name and/or the graph of one of the merchant's plans, and tags it '[write]'. This is clearly distinguishable from create_agent_office_plan_graph and copy_agent_office_plan_graph by the verb, though the description never names those siblings explicitly.

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?

Usage is implied rather than stated: 'Changes the name and / or the graph' plus the note that unsent nodes/edges are preserved signals a partial-update tool. It never says when to prefer this over copy_agent_office_plan_graph, nor that validate_agent_office_plan_graph should be run first, so the agent must infer routing.

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