quipu_path_cone

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

Annotations only declare readOnly/non-destructive/open-world; the description goes well beyond them by explaining what each verdict means operationally — in-cone pruning requires a human Decision, out-of-cone is mechanically prunable, and cannot-evaluate is never silently prunable. It also discloses hard preconditions ('refuses trajectories with no steps or no falsifier-gated verification'), which is exactly the kind of failure-mode context an agent needs before calling.

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 sentences, front-loaded with the purpose followed by the verdict taxonomy and the refusal conditions; no sentence is filler. It is extremely terse and em-dash-heavy with dense domain jargon, which slightly taxes readability, keeping it off 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?

With no output schema, the description takes on the return-value burden and does so by enumerating the three per-step verdicts and their pruning implications. Combined with the stated refusal preconditions and the fully documented input schema, an agent has everything needed to decide whether to call and how to interpret the result.

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 'trajectory', 'via', 'hops' and 'base_ns' are already documented in the schema. The description reinforces the derivation-edge concept implicitly ('no derivation edges recorded') without adding syntax, defaults or format detail for any parameter, so the schema carries the load and 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?

States a specific verb and resource ('compute the provenance cone of a trajectory') and immediately glosses it as 'which steps did its falsifier-gated verified result depend on', so the operation is unambiguous. It is also clearly distinguishable from neighbouring analysis tools like quipu_impact, quipu_path_backtest and quipu_explain by naming its input (a trajectory) and its output (per-step in/out-of-cone verdicts).

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?

Usage context is clear: use it to find which steps are load-bearing for a verified result, and the refusal conditions ('no steps or no falsifier-gated verification') tell the agent when the tool will not apply. It stops short of explicitly naming alternatives (e.g. quipu_impact or quipu_path_backtest) or stating when NOT to reach for this versus those, so it is not a full 5.

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