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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by stating that the scanner defaults to enabled=false to avoid spending PostHog Vision credits until enabled=true, which is a key side-effect. It also discloses the dependency on PostHog being connected and includes a write-tier approval requirement. This adds valuable behavioral context beyond the schema. It doesn't mention idempotency or error handling, but covers the most critical behaviors for a creation tool. A score of 4 is appropriate given the absence of annotations.

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 concise and well-structured. It front-loads the core purpose, then explains default behavior, usage, prerequisite, and approval requirements in a logical order. The bracketed permission note is an extra but relevant addition. It avoids redundancy with the schema and stays within a few sentences. It loses a point because the permission note might be better placed elsewhere, but overall it's efficient and readable.

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 creation tool with 10 parameters, the description covers the essential context: what it does, the default enabled state, spending implications, the prerequisite, and intended users. It doesn't describe the return value, but that's often implied. However, it doesn't explain the relationships between parameters (e.g., how 'scanner_type' influences 'scanner_config' or 'emits_signals'), which could be important for an agent to choose proper arguments. Since the schema covers the parameter definitions individually but not the interactions, the description could be more complete. A score of 3 reflects adequate but not exhaustive contextual guidance.

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?

The schema description coverage is 100%, so the baseline is 3. The description does not significantly add to what the schema already states; for example, the schema already explains that 'enabled' defaults to false and starts spending credits. The description mentions 'enabled=false' again but doesn't elaborate on other parameters like 'scanner_type' or 'scanner_config'. Since the schema already covers all parameters, the description doesn't need to repeat them, but it also doesn't add extra meaning beyond the schema. Thus, a score of 3 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 clearly states the action: 'Create a Replay Vision scanner on the connected PostHog project.' It also specifies the intended actors ('for the operator or analytics agent') and the use case ('when adding a new AI probe on session recordings'). The verb 'create' distinguishes it from sibling tools like posthog_update_vision_scanner or posthog_delete_vision_scanner, though it doesn't name them explicitly. A score of 4 is given because while the purpose is clear, it could more explicitly contrast with related PostHog tools.

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 provides a clear usage context: 'Use when adding a new AI probe on session recordings.' It also mentions a prerequisite ('Only works if PostHog is connected') and a permission note about approval. However, it doesn't explicitly state when NOT to use this tool or name alternative tools (e.g., posthog_update_vision_scanner for modifying an existing scanner). This is adequate but not as strong as examples that explicitly route to siblings. A score of 3 reflects the presence of context without explicit exclusions.

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