evaluate

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

The annotations already declare readOnlyHint=true and destructiveHint=false, yet the description adds non-obvious semantics: expressions are evaluated independently, and 'An expression that calls a target function runs it on the target', which is important context an agent would not get from the schema. That statement also softly qualifies the read-only framing, since target invocation may have effects, but the examples themselves are reads and there is no direct contradiction.

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?

Three short sentences, front-loaded with the purpose and immediately followed by illustrative examples. Every sentence carries information: what it does, what the input looks like, and how batching/failure behaves.

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 one-parameter tool with annotations and no output schema, the definition covers purpose, input shape, and failure isolation. The remaining gap is result shape — it says expressions succeed or fail but not how per-expression results are returned — which matters somewhat since no output schema exists.

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 100% and the single 'expressions' array is documented only as 'PRACTICE function expressions', so the description's concrete expression syntax examples add genuine meaning about expected input format. It still does not state whether expressions are evaluated in order or whether the array elements can depend on each other, which caps it below 5.

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 specific verb and resource: 'Evaluate PRACTICE functions', and backs it with concrete examples (Register(PC), Data.Long(D:0x20000000), Var.VALUE(counter), Trace.RECORDS()). An agent can tell this is expression evaluation rather than a stateful 'command' or 'run'. It does not explicitly contrast itself with siblings like command, script, or run, which keeps it at 4.

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?

'Each expression succeeds or fails on its own, so pass everything you need in one call' is real batching guidance, telling the agent not to split work across calls. However, there is no indication of when to prefer this tool over the neighboring command, script, run, or view tools, so the choice between siblings is left to inference.

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