run_write_scenario_tool

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 reasonably well: it discloses that values actually commit (verified by read-back), that steps may target different fields via step.marker, and that non-write steps are reported as unsupported. This is substantive commit/verification context. It stops short of stating prerequisites or failure behavior, so not a 5.

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 verb and write-scoping are front-loaded, which is good. But the single dense paragraph is cluttered with backticks, embedded Russian Gherkin, and internal jargon (NativeWriteSession, capture-free element addressing), making it heavier than the information content warrants.

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?

An output schema exists, so return-value explanation is not required, and the description does sketch the ScenarioResult preview. But for a 15-parameter tool with zero schema coverage and no annotations, the definition leaves far too many controls undocumented for an agent to invoke it confidently.

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?

There are 15 parameters with 0% schema description coverage, so the description must compensate and largely does not. It explains the conceptual roles of base_field, step.marker, and the scenario_json/feature_text alternatives, but most parameters (host, port, save, display, open_link, input_offset, default_value, captured_value, require_cleanup, cleanup_evidence_json, persistence_verification_json) are never described. The coverage gap is too large for a 3.

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+resource: it runs a WRITE scenario (Gherkin input_text steps or scenario_json) natively through a commit-capable session. It distinguishes itself from the broad run_scenario/run_step siblings by emphasizing WRITE/commit semantics and read-back verification. The jargon density makes it harder to parse than ideal, but an agent can tell it targets write scenarios specifically.

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?

It implies usage by declaring the write scope and noting that 'non-write steps are reported unsupported', which is a useful when-not signal. However, it never explicitly names an alternative sibling (e.g., run_scenario, run_step, write_form_value) or the condition that should route the agent to it instead. Guidance is implied rather than stated.

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