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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false) by disclosing what is held fixed (edge connectors, fixed/locked parts), what is preserved (keepouts, courtyard gaps), the bottom-side via cost model, and that placement starts from current positions unless from_scratch. It stops short of saying whether the prior placement is recoverable or how the result is persisted.

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?

Front-loads purpose and constraints, then the comparison to auto_place, then the follow-up actions — a sensible order for a 28-parameter tool. The opening paragraph is long and clause-heavy, but nearly 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?

For a 28-param mutation tool with nested objects and no output schema, the description covers the optimization behavior, the async job model (status "running", follow up via get_board_job), and the validation steps to run afterward. Return-value detail is thin, though the wait_s parameter partially covers it.

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?

With 71% schema coverage the schema already carries most parameter meaning, but the description adds real semantics: flip_cost as mm-of-wirelength per bottom-side pad whose net has top-side pins, the coupling of keepouts to routing corridors, and the t0/refine interplay. Several params (seed, rotations, net_weight, split_cost) still get no prose explanation.

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 (dense placement) and method (simulated annealing) with the optimization objective (wirelength inside the outline) spelled out. It explicitly contrasts with the sibling auto_place ("slower... and much denser"), so an agent can distinguish the two without opening either schema.

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?

Names the alternative (auto_place) and the tradeoff that selects this tool (denser but slower, with a concrete runtime figure), and says to follow up with overlapping_pairs and run_drc. It gives no explicit "when not to use" guidance or prerequisite statement beyond the schema-level design_id note.

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