session_set_fingerprint

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

With no annotations, the description carries the full burden and does well: it discloses that changes propagate to workers and HTTP headers, that navigator.languages cannot be rewritten at runtime in workers, and that a reload is required for deviceMemory/WebGL overrides to take effect. It stops short of stating failure behavior or whether overrides persist across sessions, which keeps it out of the top band.

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?

Front-loaded with verb, resource, and mechanism before the field enumeration and the caveat note. The long field list is dense but necessary given the empty schema; the only mild cost is a run-on second sentence that mixes the accepted-keys list with the runtime caveat.

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 values need no explanation, and the description covers propagation scope, runtime limitations, and the required reload. Remaining gap is edge-case behavior — what happens if the session is absent or a field is unsupported — which an agent would still have to discover by calling.

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 0% (the fingerprint object has no declared properties), so the description is the only contract, and it enumerates accepted keys exhaustively with types and units: languages as list or comma string, device_memory in GB, and nested screen sub-fields (width, height, device_scale_factor, mobile, max_touch_points). This is exactly the compensation a 0%-coverage schema demands.

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?

Specific verb ('Apply identity/anti-detect overrides') plus a precisely scoped resource ('a live session'), with the mechanism (engine-level CDP) named. The word 'live' implicitly separates it from profile-level siblings such as session_profile_set and session_profile_regenerate_fingerprint, so an agent can route correctly without opening the schema.

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?

Usage is implied by the setter framing and the operational note, but the description never explicitly states when to prefer this over session_profile_set or session_profile_regenerate_fingerprint, nor any prerequisite (e.g. that the session must be running). The 'reload the page after this call' instruction is a useful follow-up condition, but the when-not/alternative guidance is absent.

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