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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds real epistemic context – 'conditional uncertainty may worsen' and 'forecast angles are not acquired evidence' – but partly repeats the schema's note that declared origin is unverified.

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 with no obvious filler, but the front-loaded clause is jargon-heavy and the caveats are compressed into an elliptical style that costs clarity rather than saving space.

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?

An output schema exists, so return values need not be explained, but for a tool with five required nested objects at 20% coverage the description should supply more parameter and sequencing context. The epistemic caveats help, yet a caller still cannot tell what objective, assumptions or observations must contain.

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 20% across five nested required parameters, so the description must carry meaning for objective, assumptions, new_series and observations. It only gestures at data_origin, which the schema itself already documents, leaving the other four parameters undocumented.

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 action – refitting original tracks together with one new angular series – so the verb+resource is identifiable. However, phrasing like 'compute the baseline natively' and 'each counted once' is cryptic, and it never distinguishes itself from close siblings such as triangulate_tracks or stress_test_observation.

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?

There is no statement of when to use this tool versus the many observation/track siblings, and no prerequisites or exclusions. The closest thing to guidance is 'Declare synthetic/measured origin', which is an input instruction, not usage routing.

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