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

Annotations already declare destructiveHint=true, non-idempotent, non-read-only, so the safety profile is covered. The description adds value beyond that: a billing consequence (charged like a custom scenario) and the explicit rejection error code for invalid graphs — both are things an agent cannot infer from the annotations.

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 sentences, no filler, with the write nature and the validation precondition front-loaded. Every clause carries information an agent needs.

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?

This is the most complex kind of input here (arbitrary node/edge arrays), with no output schema and zero parameter documentation, yet the description covers only cost and validation. It omits what a valid node/edge looks like, whether creates return an identifier, and how it relates to copy/edit.

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% for all three parameters, and the description does nothing to explain `agent_office_plan_name`, `agent_office_plan_nodes`, or the optional `agent_office_plan_edges`. For a graph-building tool where node/edge payload shape is the crux, this leaves the parameters essentially undocumented.

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+resource ('Creates a plan graph') and adds the notable pricing trait ('priced like a custom scenario'), which separates it from read/edit siblings. It does not explicitly name the nearest alternatives (edit_agent_office_plan_graph, copy_agent_office_plan_graph), so differentiation is partial.

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 a concrete workflow prerequisite: validate with `validate_agent_office_plan_graph` first, and states the failure mode if not (refused with ERR_INPUT_AGENT_OFFICE_PLAN_GRAPH). It stops short of saying when to create versus copy or edit an existing graph.

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