bp_auto_format_graph

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

With no annotations, the description carries full disclosure burden and meets it: it reveals the topological sort, the placement rules for data/reference nodes, anchoring of events, stacking of disconnected chains, and the use of exec_python_transactional making the layout undoable. It also documents the return contract via StructuredResult outputs.

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 longer than average but front-loaded with a one-sentence summary, then organized sections for layout rules, args, returns, KB, and example. The layout rules block repeats some of the summary's content, but every part earns its place; a small amount of redundancy keeps it from a 5.

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 6-parameter mutating layout tool with no annotations, this is complete: it covers all parameters, behavior, side effects (undoable), return values, a knowledge-base pointer, and an example invocation. The presence of an output schema doesn't hurt; the description still explains what the fields mean.

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?

The input schema has 0% description coverage, but the Args section compensates fully: every parameter (blueprint_name, graph_name, x_spacing, y_spacing, start_x, start_y) has a plain-language meaning and defaults. This gives an agent more than the schema's bare titles/defaults.

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 ('Auto-arrange') and resource ('nodes in a Blueprint graph'), and the one-sentence summary clearly distinguishes it from sibling tools like move_blueprint_node or bp_validate_graph by focusing on automatic left-to-right layout. The additional details (topological sort, spacing) reinforce the specific purpose.

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 intended usage is implied by the description — 'Auto-arrange nodes in a Blueprint graph' — but no explicit when-to-use or alternative tools are named. It doesn't state that manual per-node positioning should be done with move_blueprint_node or that validation is handled elsewhere. Clear context but no exclusions.

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