triz_flow

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

With no annotations, the description carries the full behavioral burden and does add real context: the fail-closed type-check, and the caveat that outputs are candidates rather than findings. It also discloses the internal definitions used for bottlenecks, accumulation, leaks, and loops. What it omits is the practical behavior an agent needs: whether this is read-only, whether it mutates the model, and the concrete shape of the returned result.

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 purpose is front-loaded, but the body is a single sprawling sentence per clause with deep parenthetical nesting ('the performer of an insufficient, excessive, or harmful function that carries the flow's carrier and touches the path: a resistance-like output on the flow, at its position'), which is hard to parse for an agent. Definitions of accumulation, leak, and loop candidates are buried in a run-on list rather than structured. Substantial rewriting into short labeled lines would earn a much higher score.

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?

No output schema exists, so the description must describe returns, and it does enumerate the result categories (steps, declaredOnly, bottleneck, accumulation, leak, loop, harm loops). It also covers the failure mode (fail-closed type-check). The gap is that it never gives the concrete response structure or how these candidates are keyed per flow, leaving the agent to infer the shape.

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% on a single `model` parameter, so the schema already documents the input; baseline 3 applies. The description does add interpretive meaning about what a flow path is and how series order differs from function interaction, plus the constraint that boxes consecutive on a flow become adjacent for merge. That is useful but is about model semantics rather than the parameter itself.

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 and resource: 'Flow analysis ... over the model's declared `flows`', and immediately distinguishes it from function wiring ('each an ordered path of the boxes a carrier passes through, in series, which functions do not record'). It even names the sibling interaction with triz_transform merge, so an agent can tell what is unique here. It does not, however, contrast itself against the many other triz_* checks beyond that single adjacency note.

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?

Implicit usage is clear (call it on a model that declares flows), and 'Every item is a structural candidate to substantiate, not a finding' tells the agent how to treat results. But there is no explicit when-to-use versus when-not, no statement of prerequisites such as the model needing to pass the type-check before other analysis, and no routing to sibling tools such as triz_weakness or triz_transform beyond the adjacency aside.

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