logisim_verify

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

No annotations are provided, so the description carries the full burden. It discloses useful semantics (expressions checked on every input combination, state carries over between sequence steps), but says nothing about whether the circuit file is mutated, what pass/fail output looks like, or error handling for a tool that verifies behavior.

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?

Purpose is front-loaded in the first sentence before the mode enumeration, and each clause adds format detail rather than filler. It is dense but every phrase (e.g., 'x = don't care,' 'state carries over between steps') earns its place.

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?

With no output schema and no annotations, the description should also convey what verification returns (pass/fail detail, mismatch reporting), but it stops at input formats. Input-side coverage is strong, output-side coverage is absent, leaving the tool partly underspecified.

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 only 33%, so the description must compensate, and it does: it explains the format of expressions, truth_table, rows, and sequence with concrete inline examples. It omits any mention of the required path parameter or circuit, but the schema already documents those two.

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 clear verb+resource: 'Check that a circuit behaves as expected.' An agent can tell this validates circuit behavior as opposed to building or rendering. It does not distinguish itself from the ambiguous sibling logisim_check, which likely sounds similar, so it falls short of a 5.

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 description tells the agent to 'Give exactly one of' four modes and notes sequence is 'for clocked circuits,' which guides mode selection. However, it never states when to pick this tool over siblings like logisim_check, logisim_simulate, or logisim_truth_table, leaving the tool-vs-tool decision to inference.

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