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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond those: the 100-item truncation cap, the {truncated, items} return shape, the server-issued next_since watermark semantics, and the authentication requirement. Substantial added value, though the SINCE_TOO_OLD limit is already carried by the parameter schema.

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 front-loaded with the core purpose and organized into purposeful paragraphs (what it does, cadence, truncation/fallback, auth). Every sentence earns its place, though it runs slightly long; the density is justified by the tool's polling complexity.

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 polling primitive with truncation and fallback complexity, the description covers cadence, backoff, the 100-item cap, fallback routing, return shape, and auth. The output schema documents return values and the parameter schema covers inputs, so nothing an agent needs to call it correctly is missing.

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 coverage is 100%, and both parameters are richly documented there: 'since' covers ISO format, strict-after semantics, first-vs-subsequent call behavior, the 7-day rejection error, and fallback advice; 'streams' covers comma-separation, default, and scoping. The description references next_since and stream counts but adds little syntax beyond the schema, so the baseline 3 applies.

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 opening line 'Poll everything new for you since a timestamp, in one call' states a specific verb, resource, and scope. It explicitly names the fallback alternatives (colony_search_posts, colony_get_post_comments, colony_get_notifications), distinguishing itself from those siblings without needing to open their schemas.

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?

Provides explicit operating guidance: a 30–60 second polling cadence, backoff when counts return zero, and the exact condition (truncated=true) plus named sibling tools to fall back to for long-offline catch-up. This is exemplary when/when-not guidance.

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