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

Annotations already cover the read-only, non-destructive, idempotent safety profile Mendable. The description adds substantial behavioral context beyond that: it specifies the input data basis (timestamp-aligned closed-bar log returns), the full set of computations, and a deliberate omission. This helps the agent understand what the call will and will not produce.

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 description is dense but not bloated; every listed output is relevant to an agent deciding whether to invoke the tool. However, the opening sentence is very long and front-loads a large enumeration of results before the 'Use this for' guidance appears. Slightly restructuring into two sentences would improve scannability, so it falls just short of 5.

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 compensates by enumerating the returned diagnostics in detail. It also gives the data basis and a key exclusion; combined with schema defaults and enums, an agent has enough context to call the tool correctly. It stops short of describing the structure of the correlation matrix or rolling series, but those are relatively inferable analytical concepts.

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 description coverage is 71%, so the schema already documents bars, symbols, benchmark, timeframe, and rollingWindow, while market and exchange are self-documenting enums. The description does not explain parameters individually, but it does clarify the analytical intent that connects them. Baseline 3 is appropriate because the structured schema carries most of the parameter semantics.

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 opens with a specific verb and resource: 'Professional multi-asset relationship analysis on timestamp-aligned closed-bar log returns.' It enumerates concrete outputs such as correlation matrix, OLS beta/alpha, and rolling spread z-score, which clearly separates it from siblings like market_candles and market_dominance. The tool's analytical identity is unmistakable.

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?

The description states explicit use cases: 'Use this for BTC correlation, beta, pairs and relative-strength work.' It also gives an explicit exclusion: 'price-level correlation is deliberately not reported,' which tells the agent when not to rely on this tool. This is actionable routing guidance even though no specific sibling tool is named.

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