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

With all annotations false, the description carries the full disclosure burden and delivers: the draft state ('measures nothing yet'), the credit-balance dependency, validation parity with the app configurator, and the behavioral difference between omitted next_survey_at and an explicitly scheduled date. It does not contradict the annotations (readOnlyHint=false aligns with a create operation). Minor gaps remain, such as not stating that each call produces a distinct tracker, though idempotentHint=false already signals this.

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?

Five sentences, all dense and purposeful: purpose, launch workflow, validation expectation, and two parameter-behavior clarifications. The critical draft-state fact is front-loaded. Minor prose roughness ('Omitted, next_survey_at means...') and slight redundancy between the next_survey_at and frequency guidance keep it from a 5.

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 12-parameter create tool with no output schema, the description covers the trickiest behavioral semantics (draft state, launch linkage, on_demand mode, omission behavior) while the 100%-covered schema handles the per-parameter detail like custom_prompt dependencies and pricing. The main absence is any mention of what the tool returns on success (e.g., a tracker ID), which matters more here because no output schema exists. Everything required to invoke it correctly is nonetheless present.

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. The description exceeds it by adding cross-parameter and workflow semantics the per-parameter schema entries lack: what omitted next_survey_at means at start_tracker time, and how frequency=on_demand interacts with start_tracker and survey_now. It explains the orchestration between parameters rather than restating their individual meanings.

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 and resource ('Create a tracker in draft') and immediately distinguishes itself from the launch action by naming start_tracker explicitly. The draft-state framing is the key differentiator: this tool creates but does not run, which separates it cleanly from the many create_* siblings (create_project, create_surface, create_quest) and from start_tracker/survey_now.

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 workflow is explicit: create in draft, then call start_tracker to launch against the prepaid credit balance, and use survey_now for subsequent on-demand readings. The on_demand single-reading scenario is spelled out concretely. It stops short of a full when-not-to-use list (e.g., no explicit contrast with update_tracker for later edits), so it earns 4 rather than 5.

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