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

The annotations already declare readOnlyHint: true, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: the meaning of generating_brief with briefQueuedAt set (queued behind the daily cap, auto-forges at reset) versus null (actively forging). This is exactly the tribal knowledge — queueing, caps, state transitions — that an agent cannot infer from either the schema or 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?

Roughly 60 words with every sentence earning its place: purpose-and-scope in the first sentence, sibling routing in the second, and the densest operational knowledge (status semantics for the cap queue) in the third. Nothing is filler; the longest sentence carries the highest-information detail in the whole definition.

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?

There is no output schema, so the description must hint at return shape — it does, by naming the detail categories and their nesting (cluster context, derived asset types, keyword volumes). The only thing left out is the structure of the brief-availability field and edge-case return behavior, but the description correctly scopes those to get_article_brief. This is a defensible trade.

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 0%, so the description technically carries the disclosure burden, and suggestionId is never explicitly defined. However, with a single parameter whose name and strict UUID pattern make its semantics self-evident, the description's overall framing ('Get article suggestion details') makes clear the ID identifies the suggestion. The structural schema alone effectively documents this parameter.

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 ('Get article suggestion details') and concretely enumerates what's returned — metadata, cluster context, brief availability, derived assets (with examples), and target keywords. The description goes beyond the schema by naming the sibling it is not (get_article_brief) and by explaining the brief-status semantics, which is the single most important differentiation an agent needs.

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 routing: 'Call get_article_brief for the full brief' — giving the agent a clear trigger condition for the closest alternative. It doesn't explicitly discuss when not to use this tool relative to other siblings like list_article_suggestions, but for a single-ID getter with a tiny decision surface, the guidance covers the primary point of confusion.

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