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

The readOnlyHint annotation already declares the tool safe, and the description adds substantial behavioral context beyond that: the per-channel distributions rollup shape, page-through behavior, and a nuanced status semantics (queued behind the daily cap vs actively forging, with advice to re-check within a minute). No contradiction with the annotation.

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 value proposition and return fields, then moves to pagination guidance and status semantics. It is longer than minimal, but every sentence adds necessary operational detail with no filler.

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?

Given there is no output schema, the description carries the full burden of explaining the response shape, including the rollup object and status behaviors. It also covers pagination and alternates for full records and brief status, leaving little ambiguity for an agent deciding how to use the 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 schema has 0% description coverage, so the description carries most of the parameter-meaning burden. It does clarify the generating_brief status meaning and implies pagination with 'Page through suggestions,' but it does not explicitly explain projectId, limit, or cursor behavior, so coverage remains partial.

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 opens with a specific verb and resource ('List article suggestions for a project') and enumerates the exact returned fields (title, status, priority, cluster, intent, source, publishedAt, scheduledFor, and a per-channel distributions rollup). It also distinguishes itself from sibling get_article_suggestion by explicitly pointing to that tool for the full record.

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 description gives explicit guidance: use the list to spot gaps 'without per-item reads' and 'call get_article_suggestion for the full record' when more detail is needed. It also routes status-related follow-ups to get_article_brief, naming the exact alternative and conditions clearly.

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