vis_beskeder

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

The description discloses a real behavioral trait beyond the annotations (it marks messages as read, and orders oldest-to-newest), but that trait is a state mutation. The annotations declare readOnlyHint=true, so the description directly contradicts the declared side-effect profile. Per the rubric this is an Annotation Contradiction.

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?

Three short sentences, front-loaded with what the tool returns, then ordering, then the read-marking side effect, then the exclusion. No filler; the only weakness is that the side-effect sentence is buried rather than stated up front given its importance.

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?

With one optional boolean, no output schema, and annotations present, the description covers the essentials: source, ordering, side effect, and an exclusion. It is incomplete on the parameter's behavior and on whether reading is idempotent given the read-marking, which matters for an agent that may call it twice.

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 single parameter (kun_nye, default true) is never mentioned, and schema description coverage is 0%, so the description must compensate and does not. The mention that messages get marked as read indirectly hints at why an only-new filter exists, but that is inference rather than explanation of the parameter's effect or default.

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 names a specific resource and source: replies from the household via Telegram, with an explicit ordering rule ("nyeste sidst") and an explicit exclusion ("OK UGE-xxxx" messages are not here). This lets an agent distinguish it from a send-message tool, though it does not name any sibling by name.

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 framing (read household replies, e.g. what is in the fridge) and one clear when-not case is given: OK UGE-xxxx messages are not returned here because the listener handles them. However, no alternative tool is named for any case, so routing must be inferred from sibling names alone.

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