flow

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description adds genuine behavioral context: it follows through captured arguments/locals/returns, resolves object names against the event that captured them, and 'refuses by name what the recording did not capture,' which tells an agent how the tool fails on uncaptured identifiers. This is informative failure-mode disclosure that the annotations do not provide.

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 dense sentences with the core purpose front-loaded and every clause earning its place. The telegraphic style ('provenance of a value') is efficient, though slightly cryptic for a first-time caller, which keeps it from 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?

For a 5-parameter tool with two exclusive modes and no output schema, the description covers the critical disambiguation between modes and the mandatory-selection rule. The main gap is that it never hints at what the provenance output looks like, which matters more given there is no output schema to fill that void.

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 baseline is 3, but the description adds meaning the schema lacks: the semantic difference between equality-tracking (`--value`) and identity-tracking (`--object`), the mutual exclusivity requirement, and the refusal behavior for uncaptured names. It connects the parameters to tool behavior rather than merely restating formats.

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 clear purpose — tracing the provenance of a value or object — and elaborates two distinct modes (`--value` by equality, `--object` by identity), which is specific enough to separate it from the sibling set. It stops short of 5 because it never explicitly names or contrasts any sibling tool.

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 through the behavior described: equality-following vs identity-following, plus the explicit constraint that one of `--value`/`--object` is required. However, there is no statement of when to prefer `flow` over siblings like `grep`, `watch`, or `tree`, and no exclusions or alternative routing.

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