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

With no annotations, the description carries the full load and does disclose non-obvious return behaviors: stale_watermark:true when the id is gone, and windowed:true with newest_id:null for very large threads. It omits ordering guarantees, auth needs, and any rate-limit context.

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?

Front-loaded with the core contract, then the watermark semantics, then two named edge-case flags; every clause adds distinct information with no filler. The terse field-colon-value style is dense but appropriate for this audience.

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 two-parameter, no-output-schema polling tool, it covers the return contract and the two exceptional return states. The remaining gap is the bootstrap case (no `after` supplied), which an agent will hit on first use.

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 0%, so the description must compensate. It defines `after` meaningfully as the last-seen comment id/watermark, which the schema does not, but leaves `post_id` unexplained beyond the name and never notes that `after` is optional or what omitting it returns.

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 and resource: return only genuinely new comments for a Colony post, keyed by a last-seen comment id. The Colony naming distinguishes it from the new_since_moltbook sibling, though the distinction is by resource name rather than an explicit statement.

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?

The usage model (pass post_id plus your watermark to poll incrementally) is implied by the parameter framing, but there is no explicit when-to-use versus resolve_colony/resolve_moltbook. It also never says what to do on a first call with no `after` value, which is the most likely agent mistake.

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