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

Annotations are None, so the description carries the full burden. It discloses the significant behavioral trait that 'Setting enabled=true starts spending PostHog Vision credits' – a critical side-effect that should influence agent decisions. It also adds the approval requirement hint ('may require a manager's approval') which is valuable context. It does not mention concurrency, reversibility, or failure modes, but for a mutation tool this covers the most important behavioral aspects.

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 compact, with the essential purpose and key side-effect front-loaded. The approval note is appended in brackets, which is a bit unusual but still readable. No wasted sentences; each line adds value. It could be slightly shorter but stays within reasonable size for 11 parameters.

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?

Given 11 parameters, low schema coverage, no output schema, and no annotations, the description is insufficient for an agent to correctly construct a request. Critical parameters like `sampling_rate`, `credit_limit`, `scanner_config`, and `emits_signals` are not explained, and there is no mention of what the response will be (though output schema absence doesn't require explanation). The description covers purpose and the enabled side-effect but leaves many parameter semantics undefined.

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 low (27%), and the description only clarifies the `enabled` and `credit_limit` semantics (credit limit is not explicitly explained, only in the schema as a property with no description). The description names 'sampling' but not `sampling_rate` exactly, and no guidance is given for `name`, `description`, `scanner_type`, `emits_signals`, `scanner_config`. Since schema coverage is low, the description should compensate more, but it adds minimal parameter-level meaning beyond `enabled`.

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+object ('Update a Replay Vision scanner') and lists exactly what can be changed (prompt, enabled, sampling, credit limit). It also adds a clear warning about enabling spending, so an agent knows the purpose and the key side-effect. It distinguishes from siblings by naming the action 'update' versus create/delete/list, which is implicit but sufficient given the sibling names are `posthog_create_vision_scanner`, `posthog_delete_vision_scanner`, `posthog_get_vision_scanner`, etc.

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 clear context: 'Use when changing a scanner or turning spend on.' It also conditions on 'Only works if PostHog is connected.' However, it doesn't explicitly exclude the create or delete tools, nor does it mention scenarios where updating would be inappropriate, but the context is strong enough for an agent to know when to use this tool.

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