skylight_list_messages

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds real value beyond them: it discloses the auto-pagination behavior (reads the paged feed, up to 20 pages) and a prompt-injection warning about untrusted captions/comments — content an agent genuinely needs to handle the payload safely. It stops short of describing auth requirements or the returned shape.

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?

Two tight sentences, front-loaded with the core action and scope before the safety caveat. Nothing is redundant, though the parenthetical pagination detail reads slightly oddly embedded mid-sentence rather than as a separate clause.

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 no output schema and no annotations describing return structure, the description should say more about what a message record contains and how the 20-page cap is surfaced to the caller. The injection warning and pagination note are worthwhile, but the missing parameter documentation and unspecified response shape leave gaps for a feed-listing tool.

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 has 0% schema description coverage, so the description must carry the burden — and it never mentions the parameter, its format, or that it is optional. 'Posted to the Skylight frame' only obliquely hints that a frame identifier scopes the read, leaving the agent to infer parameter meaning from the schema alone.

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?

States a specific verb+resource (list messages) scoped to the Skylight frame, with the pagination ceiling ('up to 20 pages') making the read scope concrete. It does not explicitly distinguish itself from siblings like skylight_get_message or skylight_list_frames, but the name and resource are unambiguous enough that an agent can route correctly.

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 only implied: the agent can infer 'call this to see messages on a frame.' There is no explicit when-to-use guidance, no stated alternative for fetching a single message (skylight_get_message), and no note about what happens when nothing is posted or how the caller should page further.

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