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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description goes beyond that by disclosing what is returned (map hash, declared body/profile, trace, events, diagnostics, limitations) and, crucially, by bounding expectations: a passed test is not proof of combat, scripts or destination-engine gameplay. The 'bounded'/'browser-free' phrasing signals execution limits without detailing them.

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 sentences, front-loaded with the core action and ending with the key limitation caveat. Little waste, though the opening clause stacks jargon ('FREE bounded browser-free route/clearance') that costs readability for no informational gain. Each sentence otherwise earns its place.

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 complex tool with a large nested schema and no output schema, the description usefully covers the return payload, the one-of-two-input rule and the scope caveat. It remains incomplete on the scenario variants and the simulation parameters (hz, steps, profile), which an agent must reverse-engineer from the schema alone. Adequate but with clear gaps given the tool's complexity.

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 description coverage is 0%, so prose must carry the load. The description adds one high-value rule the schema does not encode — exactly one of mapId or draftId must be supplied (the schema marks neither as required and offers no mutual exclusion). But it says nothing about the scenario object's three variants (route, surface-runner, platformer), hz, steps or expect, leaving the dominant parameter essentially undocumented in prose. Partial compensation only.

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 (run a map movement test) and clarifies the two modes it covers: route/clearance checking and deterministic controller replay. The phrasing is dense with internal jargon ('FREE bounded browser-free', 'destination-engine gameplay'), but an agent can still tell this is a movement/collision test rather than a generic map preview. It does not explicitly contrast with the nearby preview_map_draft or map_workbench_context siblings.

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?

'Choose exactly one saved mapId or prepared draftId' is a genuine usage rule, and 'Save reusable scenarios in document.playtests; inspect canonical images separately' hints at where the tool fits in a workflow. However, there is no explicit statement of when to reach for this tool versus alternatives like preview_map_draft, nor any when-not guidance. Usage is implied rather than spelled out.

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