rew_decode_array

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

Annotations already declare readOnly, non-destructive, and closed-world, so safety needs no restatement. The description usefully adds that non-finite values surface as null, a genuine output-behavior detail the annotations don't cover. However, it says nothing about what happens when the decoded array exceeds max_points — truncation, error, or pagination — which is the most consequential unknown for a caller.

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?

Two short, front-loaded sentences with no filler. The format and the non-finite rule are exactly the facts an agent needs first.

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?

This is a data-conversion tool with no output schema and three undocumented parameters. The critical omission is the pagination contract: with offset and max_points present and max_points defaulting to 2048, an agent cannot tell whether one call returns the full sample set or a truncated window, which risks silently incomplete data.

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 0% across three parameters. The description clarifies only 'encoded' implicitly (Base64 float32 samples) and leaves 'offset' and 'max_points' completely unexplained — yet max_points defaults to 2048 and caps at 100000, so a caller needs to know whether this silently truncates results. The description does not compensate for the coverage gap.

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 ('Decode') plus a precise resource format ('REW big-endian IEEE-754 float32 Base64 samples'), which is unambiguous and implicitly the inverse of the sibling rew_encode_array. It stops short of explicitly naming that sibling as the counterpart, so differentiation rests on the verb alone.

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?

There is no when-to-use guidance, no mention of the encode counterpart, and no stated preconditions (e.g. that input must be REW-produced Base64, not arbitrary Base64). The agent must infer the calling context from the tool name and the format string.

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