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

Despite annotations already covering the safety profile (readOnly, idempotent, non-destructive), the description adds substantial behavioral context: history begins at the poll origin (Sept 11, 2026, 3:41pm ET), nothing before it exists, series_origin_ts is the poller's first capture and not the market open, gaps are defined as intervals > 1.5x median cadence, and it states the data is free with no key. This is exactly the kind of provenance and accessibility detail annotations cannot express.

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?

Information is front-loaded with purpose first, then provenance, then the coverage block, then args. It is dense and long, but with no output schema each clause about the return shape is earning its place; a few phrases could be tightened 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?

With no output schema, the description carries the return-value burden and does so: it names the returned series (YES price and 24h volume points), the normalized ISO close date, and the coverage block contents (span, expected vs delivered samples, gap_count with threshold, largest gaps). An agent has everything needed to call and interpret results.

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 goes further by giving concrete value formats (market as Polymarket numeric id or Kalshi ticker with the example KXFED-26SEP-T4.50, and start/end as YYYY-MM-DD). This adds real interpretive value beyond the schema descriptions rather than merely restating them.

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 gives a specific verb+resource ('Time series for a prediction market the desk polls') and pins the scope to top ~100 by 24h volume on Polymarket + Kalshi with ~15 min snapshots. It clearly distinguishes this from the coverage-check sibling get_prediction_markets, which it explicitly references, so an agent can route without opening a schema.

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?

It states intended use cases ('resolution-date theses and term-structure backtests') and names the sibling to consult first ('get_prediction_markets flags each Kalshi market tracked_15m so you can see coverage before calling'). It stops short of explicit when-not-to-use or alternative routing beyond that pre-check, so 4 rather than 5.

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