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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the bar is lower. The description adds genuine context beyond them: feeds are private by default, the operation is additive only (no mutation/deletion of existing resources), and it fails when the name is taken — effectively confirming the non-idempotent, non-destructive profile with concrete consequences.

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 compact sentences with the operation type front-loaded and zero filler; the failure mode and the additive-only guarantee each earn their place. The trailing 'POST /feeds' is a small but non-redundant endpoint anchor.

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 would normally need to say more about results, but for a create operation the key agent-facing facts — default privacy, optional group nesting, additive-only behavior, and name-collision failure — are all present. Only the shape of the returned feed object is left unspecified, which is minor here.

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 the schema already documents name, group_key, and description including lengths and the key-derivation note. The description only echoes the group placement ('optionally inside an existing group') and adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 ('create a new, empty feed'), adds scope ('private by default, optionally inside an existing group'), and leads with a 'WRITE:' marker that instantly separates it from the read-oriented siblings like get_feed and list_feeds. An agent can distinguish this from every other tool in the set without opening a schema.

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 context for when to use it (creating a brand-new empty feed, optionally nested in a group) and a useful exclusion ('does not change or delete anything existing'). It does not name a sibling alternative or a prerequisite such as verifying the feed does not already exist, so it stops short of full when/when-not guidance.

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