expressions

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

Annotations declare readOnlyHint=false, idempotentHint=false, so the agent knows this is not a pure read, yet the description never explains what state it mutates or what permissions/conditions are required. It does disclose one meaningful behavioral fact beyond the annotations: compare 'runs action between the two captures', i.e. it can drive execution (consistent with the step/continue/halt enum), which is genuinely valuable context.

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 with the purpose, then compressed into pipe-delimited signatures; every clause carries content. It is dense and telegraphic rather than verbose, though the trailing 'compare runs action between the two captures' restates what the signature already implies.

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 5-parameter tool with nested objects and no output schema, the description covers action, assertions, table, and expressions but omits the 'session' parameter entirely and says nothing about what results are returned. Adequate for the main action flows, incomplete for the full surface.

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 ~80% schema coverage the baseline is 3, and the description earns an extra point by spelling out the per-action argument shapes: assertions=[{expression,expected[,operator]}], table={index_range,columns}, and the action list for compare. This maps parameters to intent more directly than the schema's raw object definitions.

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+resource ('Evaluate C/GDB expressions') and enumerates the three operations it actually performs (assert/capture/compare), so its scope is legible. However, it never distinguishes itself from sibling evaluation tools like read_variable, read_memory, or read_registers, leaving the agent to infer the boundary.

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 action signatures implicitly communicate what each mode is for (assert compares to expected, capture snapshots, compare diffs two captures), which is usable guidance. But there is no explicit when-to-use/when-not statement and no routing to alternative tools for plain variable reads.

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