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

Annotations already declare readOnlyHint, openWorldHint=false and destructiveHint=false, so the leading 'Read only' adds nothing. The description earns credit elsewhere: it discloses ordering (newest first), that results are 'last counted' rather than live, and that get_goal is the fresh path — staleness behavior an agent could not infer from structured fields.

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 tight sentences plus a routing clause; the resource definition and ordering come first, the alternative last. No filler beyond the redundant 'Read only' opener, which is a single word-pair cost.

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 no output schema, the description carries the return-shape burden and does so by listing the item fields and the newest-first order. Combined with the staleness note and sibling routing, an agent can call this correctly; only pagination behavior beyond the schema's stated default is left implicit.

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 50%: 'limit' documents its default of 25, while 'status' is an undescribed enum. The description only says 'Filter by status' without explaining the lifecycle meanings (proposed/built/launched/done/cancelled) or how limit interacts with the newest-first ordering. It adds marginal meaning over the schema rather than compensating for the gap.

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 (list the workspace's Flows) and defines the otherwise opaque term 'Flows' with concrete examples (goals that became posts, comment-to-DM automation, page and welcome emails). It also enumerates the per-item payload (text, dates, status, plan, what it made, last counted results), so an agent knows exactly what this returns versus postfjord_get_goal.

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?

Explicitly routes single-goal lookups to postfjord_get_goal for 'fresh results,' which is a real when-to-use distinction. It also names the one filter available (status). It stops short of saying when to prefer this over other list tools such as postfjord_list_automations or postfjord_list_campaigns, but the concept definition largely does that work.

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