filings_freshness

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, but the description adds genuinely new operational context: the endpoint is free and needs no key or payment. It also discloses the measurement definitions (lag measured from SEC acceptance time, sampled over the last 200 live filings), which the annotations cannot convey. It stops short of stating caching or refresh cadence of the poller itself.

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?

The core sentence is repeated verbatim, so roughly half the text is dead weight, and the duplication sits before the useful example and usage guidance. What remains (example, when-to-use, when-not, behavior) is well ordered and front-loaded once the redundancy is skipped.

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 must enumerate the returned metrics, and it does so precisely, plus it covers cost/auth. The only gap is that it does not indicate whether the figures are cached or how often they update, which matters for a tool whose entire premise is staleness measurement.

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?

Zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-arg tool applies. The `/v1/freshness` path reference is a harmless extra hint about the underlying endpoint.

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?

The description names a specific resource (SEC filings feed freshness) and enumerates exactly what it reports: seconds since last successful poll, newest filing age, median/p95 ingest lag, per-form-type last poll, and row counts. It also explicitly separates itself from filings_search, which serves the filings themselves.

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?

"Use when you want proof the SEC feed is live" gives a positive trigger, and "Not for the filings themselves (use filings_search)" names the concrete alternative for the adjacent need. The required/not-required split is unambiguous.

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