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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description's 'stores nothing / can be repeated' reinforces rather than extends that. It does not disclose what permissions are needed, how overrides are resolved or validated (e.g., invalid path errors), or what the returned 'definition' contains, so the added context beyond annotations is modest.

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?

Two short sentences with the core action front-loaded, but 'Stores nothing. It saves nothing, so it can be repeated' restates the same point twice and duplicates the idempotentHint annotation. Trimming the redundancy would free space for the missing parameter guidance.

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 preview tool with no output schema and a large nested input object, the description should clarify what the returned definition looks like and how overrides affect it. Instead it stops at 'shows the definition,' leaving the agent without a mental model of the response or of override semantics.

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% and the body is deeply nested (profile_version_id, surface enum, overrides array with '/'-prefixed paths and a 60-item cap, product_selection with seven UUIDs). The description only gestures at 'surface' and 'optional field overrides' without explaining path syntax, override precedence, the product_selection block, or the icpId/profile_version_id relationship, leaving most parameters to be reverse-engineered from raw JSON Schema.

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 gives a concrete verb and object: it 'Shows the definition an ICP version gives a surface,' which is far more specific than the bare title. It also names example surfaces and mentions optional overrides. Slight deduction because the example surface 'campaign' does not appear in the schema's surface enum (lead_request, import, outreach, network, intent_monitor), which could send an agent hunting for an invalid value.

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?

The closing line implies this is a dry-run/simulation step that can be repeated safely, which hints at when to reach for it (before publishing or promoting overrides). However, it never explicitly contrasts with neighbors like previewAudience, previewCampaign, getIcp, or promoteIcpOverrides, so the agent must infer the choice.

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