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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is fully covered. The description adds only that returned rows carry stored scores and word counts. Pagination behavior (has_more paging) is left to the schema parameter text rather than being surfaced here.

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?

Three short sentences, zero filler, and the identification of the tool's role is front-loaded before the filter details. Every sentence carries information the agent uses.

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?

With an output schema, full parameter documentation, and complete annotations, the definition supplies what is needed to call and interpret it. Minor omission: paging/default-limit guidance lives only in the schema, not in the description body.

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 100%, so all four parameters including limit/offset paging defaults are already documented. The description merely restates the workspace_id and status filters, adding no format, default, or interaction detail beyond the schema -- the baseline 3 case.

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 plus what comes back: 'List articles with their stored scores and word counts.' It orients the agent versus the other tools by calling itself the id-discovery step, though it never names a specific sibling (article__get, article__score) the way a 5 would.

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?

Gives explicit sequencing advice -- 'Use this first to find the article ids the other tools take' -- which tells the agent when this tool is the right entry point. It also names both filter axes. No when-not-to-use or exclusion is stated, keeping it at 4.

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