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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the agent knows this mutates data. The description adds valuable context: the observations tab is removed but the underlying events persist, and the tool requires PostHog connectivity. The approval note discloses a potentially blocking permission step. This goes beyond annotations without contradicting them.

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 main sentence is dense and informative, front-loading the action and side effect. The usage note is concise, and the approval guidance is a separate paragraph that, while verbose, is necessary for correct invocation. Overall, it's efficient with no filler, though the approval section could be tightened.

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 destructive delete tool with no output schema, the description covers the action, side effects, usage context, prerequisite, and approval flow. It doesn't mention error handling or response format, but those are less critical for a delete operation. The combination of annotations and description gives the agent enough to call it safely and correctly.

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?

Both parameters (id and companyId) are described in the schema with 100% coverage, so the description doesn't need to repeat them. The description provides no additional parameter semantics, matching the baseline of 3 when the schema fully covers the parameters.

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 ('Delete'), the resource ('a Replay Vision scanner'), and a specific side effect (the observations tab is deleted while $recording_observed events remain). It distinguishes from sibling tools like posthog_update_vision_scanner and posthog_get_vision_scanner by focusing on deletion and retirement, leaving no ambiguity about what this 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?

It explicitly says 'Use when retiring a scanner,' giving a clear trigger condition. It also notes 'Only works if PostHog is connected' as a prerequisite and explains the approval flow in the write-tier note. It doesn't explicitly mention alternatives (e.g., update for modifications), but the retirement context is sufficient to route the agent appropriately.

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