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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the description adds valuable extras: the feed is public, costs $0.001 USDC per call, returns newest-first data, and is byte-identical to a named GET endpoint. This goes well beyond the annotation baseline.

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 tight sentences, front-loaded with the core purpose and key returned fields, then the cost and exact endpoint equivalence. No filler or redundant restatement of the schema.

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 simple two-parameter read-only market tool with a full input schema and an output schema, this description is complete: it states what is returned, ordering, public availability, cost, and exact REST identity. An agent has everything needed to select and invoke it correctly.

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 100%, with both product and limit already well-described. The description adds little parameter-level detail beyond the endpoint example, but it does not need to compensate because the schema already defines valid product IDs, defaults, and the limit maximum.

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 states a specific verb and resource: it is a public fill feed for a Coinbase product, listing price, size, side, timestamp, and trade id. The phrase 'newest first' plus the explicit REST endpoint identity clearly distinguishes it from related market_cbex_ticker/candles/stats tools.

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 makes the use case obvious: get recent public fills for a Coinbase product. It does not explicitly name alternatives or exclusion criteria, but the 'Public fill feed' wording and the byte-identical endpoint comparison give clear context for when to use it.

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