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

Despite no annotations carrying behavioral detail, the description discloses key behaviors: it debits credit, joins the score series as on_demand, handles concurrent calls by answering the ongoing survey, and explains two refusal conditions with specific error codes (insufficient_credits, tracker_not_active) and how to recover (top_up_url, start_tracker). This far exceeds the baseline and matches the readOnlyHint=false, destructiveHint=false annotations.

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 long but each sentence delivers distinct, necessary information: core action, scheduling context, credit impact, result retrieval, concurrency behavior, and error handling. It is well structured with front-loaded purpose and no filler, though slightly dense; it earns a 4 rather than 5 because it could be trimmed slightly without losing value.

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 single-parameter tool with no output schema, the description covers all essential operational details: the action, interaction with schedule, financial effect, result linkage, concurrency safety, and error conditions with recovery paths. Nothing an agent needs to call it correctly or interpret outcomes 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 coverage is 100% for the single parameter tracker_id, which already includes a description ('The UUID of the tracker: call list_trackers to find it.') and format uuid. The tool description does not add extra parameter-specific semantics beyond implying the tracker must be active and have credit, but that is contextual rather than parameter-level. Baseline 3 is appropriate.

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 states a specific verb ('Run one survey') and resource ('measuring tracker') and clearly distinguishes it from scheduled surveys and the on_demand frequency special case. It also names related tools (get_results, get_responses, start_tracker) that serve different purposes, so an agent can select it correctly without ambiguity.

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?

It explicitly states when to use the tool ('on top of its schedule'), when it applies to on_demand trackers, and when not to use it (tracker not active, insufficient credits). It also names alternative tools for reading results and starting the tracker, giving clear context and exclusions.

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