load_design

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

With no annotations, the description carries the full burden and delivers: it discloses that loading is additive on top of a running session, that it starts a new analysis state, that warnings (unmatched SPEF nets, missing cells, unconstrained ports) propagate to all later results, and that it returns per-step timings plus a warning digest.

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-loaded purpose sentence, then a tight parameter glossary, then behavioral caveats — every line carries information the agent cannot get from the schema, and the caveats are ordered by importance.

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?

Despite an output schema existing, it still summarizes the return payload and, more importantly, supplies the state model, sequencing, and warning-propagation context that structured fields cannot express for a setup tool of this complexity.

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%, so the description must compensate and does: it documents all five parameters in-line, including liberty's string-or-list form, the optional-but-consequential nature of sdc ("required for meaningful timing") and spef ("without it delays use wire-load / no parasitics").

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 ("Load a design into the OpenSTA session") and immediately scopes its role in the workflow ("Call this once before any analysis"), which distinguishes it cleanly from sibling reporting/tcl tools.

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?

Explicitly gives the invocation point (once, before any analysis) and routes the agent to the correct alternative: restart_session is named as required first when earlier constraints must be dropped, and get_conditions is cross-referenced for the new analysis state.

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