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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is consistent with that: proposals are approved by the owner and dispatched through Buffer, so the tool itself does not publish. It adds genuinely useful behavior beyond the annotations — per-network formatting, UTC send times, PNG card/story output, fact provenance, the well-known-spot naming constraint, and the no-'today/tomorrow' rule. It does not state volume limits, pagination, or how many posts come back.

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?

The first sentence runs to several hundred words with deeply nested parentheticals enumerating every post type, which buries the operational facts an agent needs. Later sentences are comparatively readable, but the whole is a wall of text where 'a full inventory of content types' displaces the front-loaded essentials.

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 one optional parameter and no output schema, the description carries the full burden of describing returns, and it does so in detail: networks, timestamps, links, card images, and grounding facts. The enumeration of evergreen and weekly post kinds is more taxonomy than an agent needs to call the tool, but nothing critical to correct invocation is missing.

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 100% and the schema already explains that the town slug is optional and what omitting it does. The description still adds meaning beyond the schema: results are for that town 'now, best first', which conveys ordering and recency semantics the schema does not.

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?

The opening clause, 'What Swell Cabin posts on social media, worked out from its own data,' plus the 'With a town' / 'Without a town' split makes clear this returns/generates social post proposals and lists scheduled posts. It is a noun phrase rather than a verb+resource, and the dual identity (proposal generator for one town vs. latest global proposal + scheduled list) is buried mid-sentence rather than stated up front, so the agent must read a long way to confirm the operation.

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?

The description explicitly distinguishes the two calling modes: pass a town to get that town's ranked posts, omit it to get the latest daily proposal across every town plus what is already scheduled. There is no reference to sibling tools (whats_on, town_feed) and no statement of when not to use it, so it stops short of full alternative routing.

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