run_playtest

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds genuinely non-obvious behavior: project data is never changed, screenshots land in .mcp-cache/renders/, runs can take minutes, a progressToken is needed for progress, and optional chromium/playwright prerequisites are required. This is exactly the added context annotations cannot carry, and it is consistent with (not contradictory to) the annotation set.

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?

Purpose and safety/execution notes are front-loaded, and the dense semicolon-delimited action catalogue is information-dense rather than padded. The single long step sentence is heavy but each clause earns its place by defining a distinct action; it is appropriately sized for the tool's complexity, if somewhat unwieldy to scan.

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?

Despite covering a complex, multi-action tool with no output schema, the description explains the result shape (each step with ok, a finalState, page problems such as errors and missing files), the prerequisites, and the timing/progress mechanisms. An agent has everything it needs to invoke it 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 goes further by mapping which fields belong to which action (e.g. load {mapId,x,y,direction?,party?...}, advanceText {maxMs?}, walk {direction,steps?}), a correlation the schema's flat property list does not express. It adds real meaning for a polymorphic steps array, though it does not document every field exhaustively.

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 opens with a specific verb+resource ('Play the game headless from a script of steps') and concretely frames the outcome ('report what happened'), even giving example assertions like door transfers, NPC lines, and choice branches. This clearly distinguishes it from siblings such as take_screenshot, record_video, and analyze_project.

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 gives strong context for when to use it ('no editor or running game needed', headless Chromium boot) and enumerates the exact action vocabulary an agent must choose from. It stops short of naming alternatives or explicit when-not-to-use cases, so it is clear but not fully routing-aware.

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