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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds valuable context beyond that: the returned text is untrusted, the payload includes structured result plus model reasoning, and the tool depends on PostHog connectivity. There is no contradiction with the 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?

Every sentence carries distinct information: purpose, safety caveat, usage trigger, and connectivity precondition. There is no filler or redundancy, and the most actionable information appears early.

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 simple get-by-id tool, the description covers what is returned, when to use it, a security note about untrusted text, and a runtime prerequisite. Combined with the rich annotations and full schema coverage, an agent has enough to invoke this tool correctly without an output schema.

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 description coverage is 100%, so the schema already explains all parameters. The description does not add per-parameter detail beyond framing 'id' as a scanner finding, which is a minor extension rather than a substantive improvement.

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: 'Get one Replay Vision observation' and clarifies what that contains ('structured result + model reasoning'). 'Use when reading a single scanner finding' distinguishes it from list or scanner-level tools, though it does not explicitly name a sibling tool.

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 gives an explicit trigger: 'Use when reading a single scanner finding.' It also provides a clear precondition: 'Only works if PostHog is connected.' It stops short of naming alternatives or when-not-to-use cases, but the 'single' qualifier helps route around the obvious list counterpart.

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