cad_waveform

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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the agent knows this tool can write but only within a local/closed scope. The description never explains the consequences of the write-capable actions: 'export' and 'convert' presumably produce files, but nothing states the destination, whether existing files are overwritten, or how the 180s default timeout and max_samples/max_signals caps affect behavior. With annotations present the bar is lower, but for a tool that bundles reads and writes under one entry point, this is a real gap.

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?

A single front-loaded sentence with zero filler, and the verb list is easy to scan. It is arguably over-compressed for a tool with eleven nested parameters, but nothing in it is wasted or redundant.

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 a complex, multi-modal tool: a nested request object with six actions, time bounds, sampling caps, timeouts, and a write-producing output format, plus an output schema. One sentence covering five verbs cannot prepare an agent to invoke any specific action correctly. The output schema covers return values, but the action-selection and time-bound semantics remain undocumented.

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% (only allow_empty carries any text), and the description does almost nothing to compensate. It never explains that action selects among the six modes, that start/end accept string or numeric time values, what units those bounds use, or what output_format (vcd/fst) controls. The only added value is the loose action-word list, which omits 'info' and 'signals' and so leaves the highest-traffic read modes unexplained.

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 names a concrete resource (VCD/FST waveforms) and enumerates the operations it supports (inspect, sample, summarize, export, convert), which an agent can map onto the schema's action enum. It stops short of differentiating itself from any sibling tool, and 'inspect' is a loose cover for both the 'info' and 'signals' actions, so the mapping is approximate rather than exact.

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?

There is no guidance on when to pick this tool over cad_simulate, cad_netlist, or the other siblings, and no guidance on how to choose among the six actions. The agent must infer from the description alone that 'summarize' differs from 'sample' or that 'convert' is for format change rather than inspection. No prerequisites, no when-not-to-use conditions.

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