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

Annotations only declare a safe read (readOnly, idempotent, non-destructive, closed-world); the description goes well beyond them, disclosing that figures are linear and scalable, that they are computed off today's holdings and latest correlations, that correlation drift degrades results in large moves, and that these are estimates not forecasts. That is exactly the kind of modelling caveat an agent needs to caveat its answer.

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 answer is front-loaded in the first line and each subsequent paragraph adds a distinct, load-bearing fact (line definitions, linear scaling, correlation assumption, recency/estimate caveat, sibling routing). It is dense but not padded; the density of numbers makes it slower to parse than an ideal definition.

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 semantics well, defining every reported figure and how to rescale it. The gap is on the input side: a two-parameter, zero-required tool that can be called three different ways is left to the schema to explain.

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 only 50% and portfolio_id carries no schema description at all, yet the description never mentions either parameter, does not explain holdings-vs-portfolio_id selection, and says nothing about what happens when both optional arguments are omitted. The schema's own holdings description does useful work (pointing to describe_holdings for names/ISINs/amounts), but the description adds no parameter meaning of its own.

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 opening sentence names the exact quantity produced (exposure of a strategy or account to equity markets and interest rates) and the body spells out the concrete outputs: equity beta, home-market beta, rate beta and rate duration. It also distinguishes itself from describe_historical_scenarios, so an agent can place it among the many describe_* siblings.

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 trigger phrase ('how exposed am I to rates / yields / the market' and what-ifs) and routes the past-episode case to describe_historical_scenarios by name. That is a clear when-to-use plus a named alternative, which is the top of the scale.

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