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

Annotations already declare the safe read-only/idempotent profile, so the description is free to add behavior it alone can convey. It does: rates are expressed as fractions, source URLs and quality flags are retained, and it explicitly excludes trading. That is genuine added context, though pagination/limit behavior and freshness are unstated.

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 listing the scope, followed by two short qualifiers on units and provenance. Dense but every clause carries information; only the "No trading" tail is redundant with the annotations.

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?

For a read-only board with no output schema, the description does reasonably well at conveying what comes back. It falls short on how the four filters behave, what the default limit means, and how results are ordered relative to perps.rankings.

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 4 parameters, so the description carries the full burden and largely fails it. Mentions of "HIP-3 equities" and "dated underlying references" loosely gesture at the assetClass enum and underlyingSymbol, but limit and baseAsset get nothing and no filter semantics are explained.

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?

States a specific verb (Read) and resource (cloud perpetual markets) and enumerates the returned fields: funding interval/raw/8h/simple APR, OI, premium, dated underlying references. Clear on its own, but it never distinguishes itself from the closely named siblings perps.rankings, perps.compare, perps.history, or power.board.

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?

"No trading" is the only usage boundary, and it is redundant given readOnlyHint=true. There is no guidance on when to pick this board over perps.rankings or perps.compare, nor any note on how the filters should be combined.

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