flow-add-step

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

With no annotations, the description carries the full safety/behavior burden and does so richly: it discloses that gesture-tap may be rewritten to a portable selector (with a warning when coordinates are kept), that restart-app becomes a launch step with a chromium limitation, that failures record nothing, and that in-memory state is authoritative on remote clients. This provides significant context beyond the schema.

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 description is long but information-dense, with the purpose and use-case in the first sentence and each subsequent sentence addressing a distinct operational issue (portability, launch-step handling, return value, edit/recovery). A few details could be tightened, but no sentence is purely filler.

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?

This is a complex mutation tool with no output schema, yet the description covers the return shape (`{ message, toolResult, stepCount, recorded, savedTo }`), failure atomicity, recording prerequisite, YAML editing rules, and special command transformations. The only minor gap is not explaining each return field, but the key structure is stated.

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; the description adds extra meaning by explaining that name + project_root jointly identify the open recording and by giving command-specific behavior (gesture-tap/restart-app). It does not need to restate arg/delayMs semantics, which the schema already documents.

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 opening sentence states a specific action ('Execute a tool call and record it as a step') with explicit scope (`flow named by name + project_root`). This clearly distinguishes the tool from sibling flow tools like flow-start-recording and flow-finish-recording.

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?

The description includes an explicit usage directive ('Use when recording a flow and you want to run and capture each action') plus a prerequisite pointer ('recording must already be open — see flow-start-recording'). It also gives conditional guidance (record a restart-app launch FIRST; chromium fragment caveat), but it does not explicitly contrast with flow-add-echo or name exclusions.

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