keil_read_variables

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

With no annotations, the description carries the full burden and does contribute two useful traits: reads happen in a single serialized transaction, and per-variable errors are preserved rather than aborting the batch. It omits whether an invalid name fails only that entry or the whole call, whether variables must be in scope, and any session-state requirements before the call will succeed.

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 14-word sentence with the batch limit and the partial-failure guarantee front-loaded. No filler, and every clause adds information an agent would otherwise have to guess.

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?

An output schema exists, so return-value explanation is unnecessary, and the batch/error semantics are covered. However, for a debugger tool driven by an undocumented string array, the missing name-format and session-state context is a real gap.

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 0% and the single parameter is only an untyped-in-meaning array of strings, so the description must add value. The '1..64' bound is genuinely new beyond the schema (no maxItems present), but it never clarifies whether entries are plain symbol names, struct paths, or evaluable expressions.

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 (read) and resource (variables) plus a batch scope of 1..64, which implicitly separates it from the singular sibling keil_read_variable. It never names that sibling or says explicitly that this is the multi-variable form, so differentiation is inferable rather than stated.

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 '1..64 variables in one serialized transaction' phrasing implies this should be preferred over repeated single-variable reads for batching, but that preference is never made explicit and no alternative is named. There is also no guidance on prerequisites, such as needing an active debug session or halted target.

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