run_controlled_test

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

With no annotations present, the description carries the full burden and does disclose meaningful behavior: real data fetching, a lock-in detection run against a local-background null plus a positive control, and the failure mode 'UNTESTABLE' when the reference line is not recovered. It also reveals the auth/tier distinction. It stops short of stating cost, latency, or rate limits, but the safety/behavior profile is substantially communicated.

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?

Three dense sentences; the leading 'The Lab-as-an-API:' clause is branding rather than operational content, and the middle sentence packs several internal mechanics into one line. It is not bloated, but it is jargon-heavy and not maximally front-loaded for an agent scanning for the action and its inputs.

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 fairly complex tool with no output schema and no annotations, the description covers the workflow and a key failure mode, but leaves gaps: it does not describe the shape of the 'honest verdict', the set of possible verdict states beyond UNTESTABLE, or the consequence of all parameters being optional. Adequate but incomplete for the tool's complexity.

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 description coverage is only 33% (lat and lon carry no descriptions; observable does). The description adds 'at a location' hinting at lat/lon and the synthetic-vs-live distinction that maps to the observable argument, but it does not explain formats or the valid observable values beyond what the schema already says. It partially, not fully, compensates for the low 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 states a concrete verb+resource: 'run a REAL, bounded controlled test at a location and get an honest verdict,' and names the mechanism (DeepMap data fetch + lock-in detection). It is clear what the tool does, but it never explicitly contrasts itself with siblings like verify or check_hypothesis, which appear to operate in the same hypothesis-testing space.

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 gives tier-level guidance ('Free tier runs a synthetic demo; the live lab is the authenticated tier'), which implies an authenticated tier is needed for real results. However, it offers no explicit when-to-use or when-not-to-use relative to alternatives such as verify, ground_truth, or check_hypothesis. Usage is implied rather than stated.

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