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

Goes well beyond the annotations: it discloses that approve publishes to the live site (now or at the publishing pace) and needs confirm, that retry consumes one of the month's article allowance and needs confirm, that hold prevents autopilot publication, and that reject reasons feed Seovyn's learning. Side effects, quota consumption, and the two-step confirmation flow are all surfaced.

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?

Front-loads the core action and keeps the whole definition to a single dense block that maps one clause per decision, so nothing is wasted. The semicolon-chained structure is slightly run-on and harder to scan than a list, but sizing is right for six decision branches.

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?

Covers every decision branch, the confirm/preview protocol, and the reason taxonomy, which is what an agent needs to call a six-parameter mutation tool with no output schema. Return-shape detail is minimal (only the implied preview), but the description references that preview explicitly, leaving little critical gap.

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 only 50%, and the description compensates meaningfully: it supplies the allowed reason values (inaccurate, off-brand, thin, duplicate, off-topic, bad-seo, other), explains that note is optional but teaches Seovyn, and clarifies that confirm is only set after a preview. The decision enum values are expanded with prose semantics beyond the raw enum list, though org and itemId remain schema-only.

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 ('Decide on an article') and then enumerates every decision value with its concrete effect, so an agent can distinguish it from seovyn_edit_article, seovyn_write_article, and seovyn_publish_queue. The scope of the tool is unambiguous.

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 clear when-to-use guidance for each decision branch (approve publishes, reject records a reason, hold suppresses autopilot, retry re-writes a failure, publish_refresh/discard_refresh apply to refreshed live articles) and flags which branches need confirm. It does not explicitly route to sibling tools such as seovyn_edit_article for text changes, so it stops short of full alternative coverage.

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