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

Beyond the readOnly/idempotent annotations, it discloses substantial behavior: it is an event feed not a validated signal, the long-only regime gate fails in bear tapes, auction windows are excluded as artifacts, provisional=true flags uncalibrated live detection, and degraded feeds mimic calm tapes. That is exactly the kind of non-obvious context annotations cannot convey.

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 purpose is front-loaded and every caveat carries real signal (coverage.completeness warning, provisional flag). It is dense and run-on with a nested clause structure, but no sentence is filler.

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 does the heavy lifting by describing the row contents (percentile, side, pre-event context, tradeable flag, breadth). It stops short of enumerating all returned fields, but an agent has enough to interpret results and know to check coverage before concluding quiet.

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 meaning the schema lacks: it defines tradeable_only concretely as 'DROP context + Q3/Q4' and explains row_semantics (peak vs latest). include_events and min_pctile are not elaborated beyond the schema, keeping it at 4 rather than 5.

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 leads with a specific verb+resource ('WHICH tickers are having their order flow ABSORBED') and delimits the scope as a cross-section ('one row per ticker'), which cleanly distinguishes it from the per-ticker sibling absorption_ticker. An agent can tell what it returns without opening the 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 gives an explicit use case ('Use for who is absorbing selling today?') and several contextual caveats (regime gate long-only, auction windows excluded, check coverage.completeness). It stops short of naming the sibling absorption_ticker as the single-ticker alternative or stating explicit when-not-to-use conditions, so it's clear but not fully routing.

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