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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds genuinely non-obvious context: a $0.001 USDC charge per successful call via x402 on Solana, plus an HTTPS endpoint equivalent to the MCP tool. Cost and payment/auth requirements are exactly the kind of behavioral detail annotations cannot convey. It stops short of saying what the call returns (an integer count), which is the only gap.

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?

Front-loaded with the definition, then examples, then the domain, then the commercial terms and endpoint — a sensible ordering with no filler. The only redundancy is repeating the 1-to-1000000 range that the schema already encodes.

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 single-integer pure function with a fully annotated read-only profile and no output schema, the definition supplies everything needed to invoke it correctly, including the domain and payment model. The one omission is the return type, though the examples make the integer result inferable.

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% and the single parameter carries only minimum/maximum bounds, so the description must supply meaning. It does: n is the Collatz starting value, with three worked examples showing exactly what count is produced for n=1, 6, and 7. The restated range 1..1000000 duplicates the schema bounds and adds nothing.

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-and-object: computes the Collatz glide of n, defined precisely as 'the number of steps until a value strictly below n'. That definition is what separates it from the many sibling tools like collatz_steps, collatz_length, and collatz_drop, so an agent can choose without opening a schema.

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 worked examples (glide of 1 is 0, of 6 is 1, of 7 is 11) give an agent concrete context for when this definition applies and how it differs from total-stopping-time tools. It never explicitly names an alternative or an exclusion, so the routing guidance is implied through the definition rather than stated.

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