Suggest a fix

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

Annotations only declare readOnlyHint=false and openWorldHint=false. The description adds real behavioral context beyond that: it is a mutating write that overwrites prior suggestions for the same step, works both during and after recording, and directs the agent to ground diagnoses in concrete evidence (error explanation, page text, screenshot, console/network errors).

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?

Front-loaded with the core action, followed by the step-number sourcing, evidence expectations, and replacement semantics. It is dense but every sentence carries distinct, actionable information with no 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?

For a 4-parameter mutation tool with full schema coverage and no output schema, the description covers everything an agent needs: what to write, which step to reference, how to diagnose, how to categorize the target, and what happens on repeat calls.

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 genuine meaning: it explains where 'step' numbers originate and that 'cause'/'target' should reflect an app-vs-test-vs-environment diagnosis, giving the enum values practical intent beyond the schema's bare listing.

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 (add) and resource (suggested fix for a failed step in the recording's report) and names exactly where the result surfaces ('AI agent's suggested fix' column). An agent can distinguish it from siblings like assert_text or stop_recording without opening the schema.

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?

Explicitly says which step numbers to use (from stop_recording's failedChecks / toolErrors, or failed tool calls during recording) and when the tool can be called (during a recording or after stop_recording). It also states the idempotent behavior — calling again for a step replaces the earlier suggestion.

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