skylight_list_messages

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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds a valuable warning that captions/comments are untrusted user-generated data, which is beyond the annotations. However, it does not disclose behavioral details like pagination, ordering, or the effect of the optional frameId parameter. The addition is modest but does not contradict 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 two short sentences: the first states the core purpose, and the second adds a security caution. It is front-loaded and contains no wasted words, achieving clarity with minimal length.

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 list tool, the description is adequate but leaves gaps. It does not clarify whether frameId is required (it is not), whether listing all messages is possible without a frameId, or what the return format looks like (no output schema). The safety warning is helpful, but an agent might need more detail on the parameter's optionality and the expected response.

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 frameId is never explained in the description. With schema description coverage at 0%, the description must compensate, but it only mentions 'messages posted to the Skylight frame' without clarifying the role of frameId or whether it is optional (as indicated by 0 required parameters). The agent is left to guess its meaning and usage.

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 uses a specific verb+resource: 'List messages posted to the Skylight frame.' This clearly distinguishes it from siblings like skylight_get_message (singular) and skylight_list_events. The scope is precise and immediately understandable.

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 includes a security note about treating captions and comments as data, which is useful context, but it does not provide guidance on when to use this tool versus alternatives (e.g., skylight_get_message for a single message). No exclusions or explicit routing to other tools are given, so the usage context is partially implied but not fully specified.

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