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

With no annotations, the description carries the full burden, and it delivers: it discloses the diff semantics (since-based polling), operational definitions (stale = no payout for 24h+, stopped trading = no 24h volume), and output contents (payout status, reward amounts in quote asset and USD). Missing only minor items like auth/rate limits/failure modes, which are low-stakes for a read-only poll 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?

Four purposeful sentences with no fluff: scope + change types, output contents, polling contract, then use-case routing. Front-loaded with the core question, and every sentence earns its place for a tool with this complexity.

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?

Given no output schema and no annotations, the description effectively documents both the input contract (polling pattern, thresholds) and the output semantics (change types, payout status, reward amounts). Slightly thin on edge-case/error behavior, but complete enough for an agent to correctly invoke and interpret results from this alert-poll tool.

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 baseline is 3, but the description adds real meaning beyond the schema: it explains the `since` polling contract (previous checked_at), maps '24h+' to the stale_after_hours default, '10%+' to min_holders_change_pct, and 'up to 25' to maxItems. This ties the parameters to their operational semantics.

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+resource scope: a diff/alert tool reporting 'what changed' for up to 25 StonkFun reward coins since the last check, enumerating exact change types (payout landed, stale, stopped trading, holders moved, rewards paid). This clearly differentiates it from siblings like check_alerts and the broader stonk_* family without needing to inspect schemas.

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 explicit usage context — 'Pass the previous checked_at as `since` on each poll' and the use cases 'did my reward coins pay today?' or watching a stonk portfolio. This is clear, actionable guidance, though it never names alternatives or when NOT to use it, so it falls short of a 5.

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