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

Annotations already declare readOnly=true, idempotent=true, destructive=false and closed-world, so safety needs no restating. The description adds genuine behavioral detail beyond that: the BIP-141 weight basis, vsize = ceil(weight/4), fee rounded up to whole sats, and optional fiat conversion at a user-supplied BTC price — enough to predict the numeric output shape.

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?

The first three sentences are front-loaded and dense with useful formula detail. The trailing boilerplate ('Supply units or modelVersion only when listed in inputSchema. Follow its required fields and exact choices.') is schema-repeating, and the reference to a 'units' field that does not exist in this schema is noise that could mislead.

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 the description needn't document return values, and it covers the core computation, rounding, and optional fiat conversion adequately for a two-parameter calculator. Gaps are the multisig m/n semantics and the asymmetric input/output type enums, which an agent must still read from 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 0% at the top level, so the description must carry the burden and it only partially does: it clarifies that inputs/outputs are counts plus script types, and that sat_per_vbyte is the fee rate and btc_price is the user's own fiat figure. It adds nothing about the multisig m/n parameters, the distinct input vs output type enums (e.g. p2sh, p2wsh appear only on outputs), or the nested 'inputs' wrapper shape.

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 opens with a specific verb and resource: 'Estimate a Bitcoin transaction's weight, vsize and fee from input/output counts and script types.' The 'Bitcoin' qualifier plus the BIP-141 weight framing distinguishes it from the evm_fee and solana_fee siblings without needing to open their schemas.

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?

It gives invocation-oriented guidance ('Put tool fields inside inputs', 'Do not pass the REST calculator field inside MCP arguments'), which tells the agent how to call it, but never states when to prefer this over sibling fee tools or when it is inappropriate (e.g. non-Bitcoin chains). Usage is implied by the tool name and chain scope rather than stated.

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