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

Annotations already cover idempotency and openness, and the description adds genuinely non-derivable context: the computation uses actual ancestor base fees, ceiling arithmetic and observed relay/mempool floors, which tells an agent the output is empirical rather than conservative. It also discloses the per-call price (20 sats or US$0.02 USDC), a critical pre-invocation fact absent from annotations. It could go further on how the payment/L402 handshake proceeds, but the core behavioral profile is well covered.

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?

Three dense sentences, front-loaded with what the tool computes before the encoding details and the exclusions. The telegraphic 'package=...' fragment is efficient in context, and no sentence is filler. Slightly clipped prose costs it a point but nothing is wasted.

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 an output schema present, return values need not be explained, and the description correctly omits them. For a paid, single-parameter computational tool, the combination of scope, exclusions, input encoding and price is sufficient to call it correctly. Only the payment flow mechanics are left largely to the schema.

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 100%, so the parameter baseline is 3. The description restates the package grammar (txid:target_sat_vb:child_vbytes[,child_vbytes...]) and the 25-size cap, both of which already appear in the schema, adding no new meaning. It says nothing about the payment parameters beyond what the schema documents.

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 resource and computation: CPFP fee-budget scenarios for a mempool transaction plus its ancestors, and immediately pins down the input encoding. It is clearly distinguishable in kind from siblings like analyze or score, though it never names a sibling to contrast with. Purpose is unambiguous.

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?

Gives explicit when-not guidance: 'Not transaction construction, package-policy validation, broadcast or a confirmation guarantee' cleanly fences off four adjacent capabilities an agent might otherwise assume. What's missing is positive routing — it never says which sibling (e.g. analyze or check_outputs) to use when the agent actually wants construction or policy validation.

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