quipu_path_backtest

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

Annotations already declare readOnly=true, destructive=false and openWorld=true, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: it distinguishes a genuine zero-match result from an unevaluable outcome, and states it refuses patterns it cannot compile — which tells the agent how to interpret failure rather than success.

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?

Two compact sentences, front-loaded with the 'Golden paths' label and then the operation, with no filler. It is dense in domain jargon (gp-grammar/1, work-item topic, pruned candidate) but no sentence is wasted.

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 must gesture at return values, and it does via 'which past trajectories ... would have conformed' and 'how did their work items close'. Combined with the 0-matches vs cannot-evaluate distinction, an agent has enough to call it and read the result, though the shape of the report itself remains unspecified.

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 schema already documents exemplar, omit and base_ns, making 3 the baseline. The description does add relational meaning by defining the candidate as the exemplar minus the omitted steps, but it says nothing about base_ns or the IRI form expected for omit entries.

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 names a specific verb (backtest) and a precise resource (a pruned candidate: exemplar trajectory minus omitted steps), plus the evaluation criterion (past trajectories sharing a work-item topic conforming to gp-grammar/1). It is clearly distinct from every sibling listed, though it never explicitly contrasts itself with nearby tools like quipu_path_cone.

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 implied — you invoke this once you have an exemplar plus an omit list and want to know whether history would have conformed. There is no explicit 'use this instead of X' routing and no statement of preconditions (e.g. the candidate must be compilable, which is only hinted at via the refusal clause).

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