contract_assertion_tool

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does a good job by specifying exactly what gets removed under each strategy (target and less-entrenched dependents, edges only, all descendants), which is crucial for a destructive operation. However, it omits details about reversibility, return behavior, or broader project side effects, preventing a top score.

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?

Two sentences with no wasted words. The first sentence front-loads the primary action and the second efficiently lists all three strategies with parenthetical clarifications. The structure makes the tool easy to scan and understand.

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?

The description is complete for the core operation and strategy selection, but since there is no output schema and no annotations, it should also clarify what the tool returns after contraction (e.g., updated theory, success status) and any potential error conditions. Without this, an agent may be uncertain about postconditions for this destructive theory operation.

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?

The input schema provides no descriptions for parameters, and the description adds substantial meaning to the 'strategy' parameter by explaining all three possible values and their effects. 'nodeId' and 'projectId' are not explicitly described, but their roles are strongly inferable from the tool's purpose and names. This compensates for the zero schema coverage well, but not perfectly.

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 uses a specific verb-resource pair ('Contract (remove) an assertion from the theory') and immediately distinguishes the tool from siblings like add_assertion_tool and revise_theory_tool by naming AGM contraction and listing three concrete strategies. The purpose is unmistakable and robustly differentiates from other 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?

The description clearly implies when to use this tool: when removing an assertion via AGM contraction, and it even provides guidance on selecting among strategies (entrenchment, minimal, full_cascade). However, it does not explicitly name alternatives or conditions for when not to use this tool, so it falls short of an explicit when/when-not statement.

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