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

Goes beyond the annotations by disclosing real behavioral consequences: remaining steps are renumbered, the returned list reflects new 1-based indices, and deleting the appLaunch step at index 1 is rejected. The annotations already flag destructiveHint/readOnlyHint, so this extra operational detail is genuine added value.

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?

Four tight sentences; the core action and its constraint come first, followed by rationale, side effects, and parameter sourcing. No filler or repetition of the title.

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 two-parameter mutation with no output schema, the description covers the action, the edge case (index 1), renumbering, and where to get the index. It could briefly note whether a delete can be undone (e.g. via flow_recording_revert), but otherwise it is sufficient to call correctly.

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 provenance the schema lacks — telling the agent to source stepIndex from a flow_recording_action or flow_recording_get response, which prevents guessing an index.

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 ('Delete one step from an in-progress recording') and scopes it with 'before flow_recording_save', immediately distinguishing it from the save/list/get siblings. An agent can tell exactly what this tool mutates.

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?

Gives clear context (fix a mis-recorded assert or stray tap 'without discarding and re-recording the whole flow') and the precondition that the recording is in progress. It does not, however, mention the close alternative flow_recording_replace_step, which an agent might prefer when editing rather than removing a step.

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