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

With no annotations, the description carries the full burden and does well: it discloses cost ($0.05/call), the billing source (clink shop credits via an existing key), that top-ups are paused, and that failed/empty calls are free. It also documents ordering and dedupe behavior. It does not cover rate limits or error semantics beyond the free-call rule.

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-loaded with the core capability in sentence one, followed by the operational constraint and pricing. Every clause is informative, though the billing sentence is dense and could be tightened.

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?

No output schema exists, and the description compensates by describing the return shape (combined tweets, dedupe, per-handle counts, cursor). Cost and auth context are included, making it largely sufficient for a 3-parameter tool, with only rate/error behavior unstated.

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%, so the baseline is 3, but the description adds real value beyond the schema: the 2-50 handle range (schema only shows comma/space-separated syntax) and the semantics of the since-cursor ('only-what's-new next time'). Only 'limit' is left to the schema, which already documents it fully.

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 concrete verb+resource: batch-fetch recent tweets for 2-50 handles in one call, with the output shape (combined, newest first, deduped, per-handle counts, since-cursor). The 'No from:-OR-splitting' note implicitly distinguishes it from hand-built multi-handle search queries, but no sibling tool is named, so differentiation is inferred rather than explicit.

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?

Usage is implied: use this for multi-handle watchlists rather than OR-splitting a query, and reuse the since-cursor for incremental fetches. However, it never says when to prefer x_person, x_search, or x_digest instead, and there are no stated exclusions beyond the from:-OR note.

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