create_profile

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

Annotations already indicate the tool is not read-only (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds valuable behavioral context: the profile is created on disk, it is not launched, it fails on duplicate names, and it is 'allowed for the agent.' It does not contradict annotations and provides a clear side-effect picture beyond the boolean hints.

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 description is three sentences with zero filler. The core action and primary constraint (name uniqueness) are front-loaded, and the alternative tool is named early. Every sentence earns its place, and the structure makes it easy 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?

With no output schema, the description covers the essential outcomes: success (profile created and allowed) and failure (name already taken). It also clarifies the tool's limitation (does not launch) and points to relevant siblings. Minor omission: it does not state what the return value is on success, but that is unlikely to be critical for a creation tool. Overall, it is sufficiently complete for correct invocation.

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 schema already documents all five parameters thoroughly. The description adds one extra piece of semantic context: that proxy, note, and category can be set later via set_proxy and profile_note, which implies they are optional at creation time. This goes slightly beyond the schema's per-field descriptions, so a 4 is justified.

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 states a specific verb and resource ('Create a new, empty Chrome profile on disk') and immediately distinguishes it from a sibling ('It is not launched: call start_profile for that'). It also mentions the failure condition that differentiates it from list_profiles. This gives an agent a precise, unambiguous understanding of what the tool does.

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 description explicitly states when not to use this tool ('It is not launched: call start_profile for that') and provides a prerequisite check ('use list_profiles to see existing names') to avoid a known failure. It also notes that proxy, note, and category can be set later with set_proxy and profile_note, guiding the agent on alternative workflows. This is exemplary usage guidance.

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