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

Annotations already declare idempotentHint=true and destructiveHint=false. The description adds valuable behavior: immediate first survey unless next_survey_at is in the future, restart resumes schedule, insufficient_credits response with top_up_url, and no-op on active tracker. These details go beyond annotations and clarify side effects and error handling.

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?

The description is dense but every sentence adds essential behavior. It starts with the core action, then covers timing, restart, error handling, and idempotency, with no redundant or vague phrases. Structure is logical and front-loaded.

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 no output schema, the description fully covers start/restart semantics, scheduling nuances, credit failure handling, and idempotent behavior. Nothing an agent needs to call it correctly is missing.

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 covers the single parameter tracker_id with format and description ('call list_trackers to find it'). The description does not add new parameter semantics, so baseline 3 is appropriate given 100% schema coverage.

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 clearly states the action: 'Start or restart the measurement of a tracker against the prepaid credit balance.' It distinguishes from siblings by explaining restart behavior, paused state, and active state, making it unambiguous which tool to pick.

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 explains when to use it (start or restart measurement) and when it has no effect (active tracker). It also implies alternatives like pause_tracker by mentioning restarting a paused tracker, and warns about credit requirements. It lacks an explicit 'use X instead' statement but gives sufficient context for correct selection.

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