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

Annotations already cover read-only, non-destructive, and closed-world status. The description adds real behavioral context beyond them: nightly/EOD refresh cadence, the ~330-stock coverage universe, and the scoring method (recency-weighted regression on log-closes). It does not state caching or latency, but the added timing and methodology are substantive.

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 what the ranking is and how it is computed, then the seven cuts, then the mirror URL and cadence. Dense but every clause carries information; the only near-redundancy is the URL, which does help identify the canonical source.

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 and no required parameters, the description must carry the 'what comes back' burden; it names the seven ranking views and the scored universe, which is adequate for selection. It stops short of describing the row shape or ordering guarantee, a minor gap for a 2-parameter read 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 the baseline is 3, but the prose maps enum values to meaning the schema labels alone do not convey — e.g. 'rising fastest (21d)', 'this week's biggest moves (5d)', 'steadiest builders (63d)' — clarifying the lookback window behind momentum/short-term/quarter. The limit parameter adds nothing beyond the schema's own 1-25/default-10 description.

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 subject and scope: the nightly Directional Flow trend-quality score, its methodology (recency-weighted regression on log-closes), ~330 covered stocks, and seven ranking cuts. An agent immediately knows what this returns. It does not distinguish itself from the sibling get_ranking, though the named endpoint (closelook.net/stocks/rankings/directional-flow) implicitly does.

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?

Enumerating the seven cuts (top scores, rising fastest, biggest moves, steadiest builders, still getting stronger, getting weaker, falling fastest) implicitly tells the agent which view to pick, but there is no explicit when-to-use / when-not guidance and no routing versus get_ranking or get_signal_scores.

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