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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds two useful operational facts not in annotations: the supported universes and the 200-row page cap. It does not say which session the 'daily snapshot' reflects (freshness/staleness), whether results are deterministic, or that pagination via offset requires a stable sort — the things an agent actually needs when chaining pages.

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?

Two short sentences, front-loaded with the core action, no filler. It could be one sentence without loss, but nothing is wasted.

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?

An output schema exists, so return-shape explanation is not required, and annotations cover safety. For a tool with a large nested filter surface and a sibling preset workflow, though, the description omits snapshot freshness, filter combination semantics (AND across fields), and when pagination is needed — meaningful gaps for correct invocation.

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?

Top-level schema description coverage is reported as 0% and the single `request` parameter is undocumented, so the description must carry meaning — it does establish that the request bundles filters, sorting and pagination, and names the three universes (also constrained by the StockIndex enum). It says nothing about the ~35 filter fields, default limit 50, or the default sort of change_percent desc, leaving the bulk of parameter meaning to the nested schema.

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 and resource ('Screen the daily snapshot') plus the three mechanisms (typed filters, sorting, pagination), which is concrete enough to distinguish it from read-only snapshot siblings like get_market_snapshot. It does not name run_screener_preset or list_screener_presets, so the boundary with the preset path is inferred rather than stated.

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 no when-to-use guidance and no exclusions; nothing tells an agent to prefer run_screener_preset when a saved screen exists or to call list_screener_presets first. The only context offered is the universe list and the page cap, which are capability facts, not usage routing.

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