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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered; the description adds real context on top: output is a compact board, the bank-exposure cross-read is display-only and does not feed any institution score, and series data must be fetched elsewhere. It stops short of disclosing freshness/cadence for the change-point state, which matters for a regime board.

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?

One front-loaded sentence lists the payload fields, followed by two short constraint clauses — no filler. The field list is dense but every item earns its place given the absence of an output schema; the jargon ('log-SR statistic') is not unpacked, a minor cost.

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 parameters, no output schema and full annotation coverage, the description carries the remaining burden and does so: it enumerates return fields, flags the display-only nature of one of them, and redirects to REST for series. Only the update cadence and whether the board can be empty/undefined are unaddressed.

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?

The schema takes zero parameters, so there is nothing for the description to disambiguate — baseline 4. The description correctly implies a single fixed, unscoped board rather than a filterable query, which sets the right expectation.

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?

A specific verb ('Read') plus a named resource ('compact BTC/ETH Crypto Regime board') and an enumeration of the exact readings it returns: change-point state, log-SR statistic, last shift, observation count, bank-exposure cross-read. It doesn't explicitly name which sibling (crypto_exposure_board, stablecoin_rails_board) to use instead for the neighbouring questions, so it falls short of full sibling differentiation.

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?

Usage is implied rather than stated: 'Time-series paths stay on REST' and 'display-only cross-read' tell the agent what this tool will not give (historical series) and roughly where it belongs, but there is no explicit 'use this when...' or named alternative for the exposure-side question. The 'not investment advice / feeds no institution score' lines are disclaimers, not routing guidance.

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