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

With no annotations present, the description carries the full burden. It does disclose genuinely useful behavior beyond the schema: change-detection semantics, the two excluded categories of updates, and the token-light incremental polling model. It says nothing about ordering, permission requirements, or what happens if the cursor is stale or omitted.

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 short sentences with no filler, and the most decision-relevant fact (changed-and-republished only) is front-loaded. The jump from exclusion rules to cursor advice is slightly abrupt but nothing is wasted.

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?

An output schema exists, so return values need no explanation, but the tool has six undescribed parameters and zero annotation coverage. For a filtered incremental-poll tool, the description should at minimum characterize since, limit, and the filter dimensions; instead it explains only the cursor.

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% across six parameters, and the description only explains cursor (save it, replay it). The meaning of since, limit, source, category, and lang is left entirely undefined, including whether since is a timestamp, an ISO string, or a cursor-like token — a significant gap for a polling endpoint.

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 gives a specific verb and a precise resource subset: articles whose existing content_hash changed and were republished. That 'changed-only feed' framing distinguishes it in spirit from listing/searching siblings, but no sibling is named, so the agent must infer the boundary itself.

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 tells the agent how to operate the tool incrementally (save next_cursor, pass it on the next poll) and what is deliberately out of scope (new article creation, async enrichment). It never states when to prefer it over portal_list or portal_search, so the alternative-selection guidance is implied rather than explicit.

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