P&ID: From Spec

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

Annotations supply only readOnlyHint=false, so the description carries the real burden and delivers: full-transaction rollback on any bad item, the error naming the offending path (`lines[2].to`), cancellation behavior leaving no half-drawn sheet and reverting to the UNDO Mark so the engine never stalls at a prompt, logging when the rollback itself fails, and up-front refusal of non-finite coordinates/rotation/scale/stub. This is unusually rich behavioral disclosure beyond what the annotation provides.

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 atomic-transaction intent is front-loaded and nearly every clause carries operational weight (error naming, cancellation, validation, dry-run). It is dense, with long nested parentheticals, but for a tool with this much non-obvious failure behavior the length is largely earned.

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 nested-spec, output-schema-backed batch tool, the description covers the transactional contract, failure modes, cancellation recovery, validation preconditions and the dry-run alternative. An agent has enough to invoke it correctly and anticipate outcomes, even though the output schema already documents returns.

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 100%, so the baseline is 3, but the description adds meaning: `dry_run` returns planned vertices and crossings without drawing, and it documents that the response carries the read-back graph and critique issues. The `spec` object shape is left to the schema, which is adequate given full coverage.

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 states a specific verb+resource: it places equipment, valves, instruments and connectors and then draws every line port-to-port as a single atomic operation. That clearly separates it from the one-at-a-time siblings (pid_symbol_insert, pid_line_draw) by implication, but it never names an alternative explicitly, so it stops short of the top score.

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 explains what `dry_run` is for (validate/route without touching the drawing), which is genuine usage guidance, but it never says when to choose this whole-sheet generator over the granular pid_* tools or how it relates to transaction_begin/commit. Usage context is implied rather than stated.

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