track_variable

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

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the agent knows this mutates state non-destructively. The description adds that tracking runs 'in the background' and that 'get' returns samples for trend/leak analysis, but is silent on resource cost, whether a running tracker must be stopped, or interval limits.

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 dense sentence that front-loads the tool's nature and then maps each action to its inputs/effect. No filler, and the most important scope statement leads.

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, the description carries the return-value burden and does explain what 'get' produces (sampled data for trend/leak analysis). It omits what 'stop' or 'start' return and the default-session behavior, leaving minor gaps for a 4-parameter tool.

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% so the baseline is 3, and the description adds conditional parameter meaning: 'start' specifically requires variable + interval_ms, and 'get' returns sampled data. This clarifies where the schema just says 'For start: ...' without linking the pairing requirement.

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 ('Background variable tracking') and enumerates the three actions with their effects, so an agent understands this is a polled-sampler rather than a one-shot read. It does not explicitly name sibling read_variable, so the differentiation from a simple read is only implicit.

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 per-action semantics (start/stop/get) imply the workflow of starting a tracker, stopping it, and then fetching samples. However, there is no explicit guidance on when to prefer this over read_variable or how the background tracking interacts with the debug session lifecycle.

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