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

Annotations only declare readOnlyHint=true; the description adds real behavioral knowledge beyond that: what fields each record carries, the 25,000 vs 280 character split, and an explicit null-handling rule that prevents an agent from silently defaulting to 280. It stops short of describing pagination, ordering, or empty-result behavior for a list tool.

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?

Purpose is front-loaded and the character-limit constraint follows immediately with no filler. The conditional null rule is slightly repetitive of the preceding sentence but is short enough to earn its place as an explicit fallback instruction.

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 does well to name the two key record fields an agent needs, but it does not sketch the rest of the returned record shape. Combined with five undocumented input parameters, an agent can invoke it but cannot confidently predict filter behavior or the full result structure.

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 0% across five parameters, so the description must carry the burden. It only implicitly covers username ("search by username") and site_id/domain ("filter by site"), leaving query, account_name, and the domain-vs-site_id distinction entirely undocumented, including whether the filters combine or how matching is performed.

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?

"List connected X (Twitter) accounts" states a specific verb and resource, and the follow-on sentence names the two narrowing modes (username search, site filter). It does not distinguish itself from adjacent lookups such as get_me or get_account_context, so an agent cannot rule those out from the text alone.

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 gives strong downstream guidance — read premium and max_tweet_length before drafting tweet content, and ask the user when the limit is null — which is genuinely useful workflow routing. It gives no guidance on when this tool should be chosen over the sibling account-context tools, so selection guidance is only implied.

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