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

With no annotations provided, the description carries the full burden. It discloses key behaviors: verification happens against headers bsv.cx syncs itself via P2P, never against an explorer; the user sends only the proof, the server folds the root itself; and the result is confirmed/rejected/inconclusive. It also notes it's free. However, it omits operational details like rate limits, authentication requirements, or how recent the synced headers must be, which could affect reliability. Yet the core trust model and expected outcome are well disclosed, so a 4 is warranted.

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 description is longer than typical but each sentence adds information: format list, trust model, scope, and fee status. It front-loads the core purpose and immediately distinguishes from explorer-based verification. Some redundancy exists (e.g., 'NOT an explorer' and later 'never have to trust bsv.cx' repeat the same idea), but overall it's efficient and well-ordered. A slightly tighter version could score a 5, but this is acceptable.

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 tool with 6 parameters, 3 distinct input formats, and no output schema, the description is quite complete. It explains the valid input combinations, the expected result types, and the trust model. It stops short of discussing error cases (e.g., what happens if a proof is malformed or a header is unavailable) and doesn't disclose any rate limits or usage restrictions beyond 'free'. Given the complexity, the coverage is strong but not exhaustive, so a 4 is appropriate.

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%, so each parameter has a basic description, but the tool description adds critical semantic context beyond the schema. It explains parameter interdependencies: bump must be paired with txid, nodes/index/height apply only to raw TSC proofs, and which combinations correspond to which proof types. This is valuable because the schema alone lists parameters flatly without flagging these dependencies or usage patterns, so the description meaningfully aids correct invocation.

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 precise verb and resource: 'Verify ANY Bitcoin (BSV) Merkle inclusion proof' against bsv.cx's own headers. It lists concrete input formats (BEEF, BUMP, raw TSC), contrasts with explorer-based verification, and names the result outcomes (confirmed/rejected/inconclusive). This clearly distinguishes it from sibling tools like verify_hash or archive_url, which handle simpler hash anchoring or archiving rather than full Merkle proof verification.

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 intended use context explicit: 'the trustless core' and 'Works for ANY txid's proof, not just bsv.cx's own anchors.' It explains when to use it (you have a proof and want trustless verification) without requiring trust in bsv.cx. However, it does not mention when not to use it or name alternatives among siblings (e.g., when only a hash is available, verify_hash might be more appropriate). The guidance is clear for the main use case but lacks explicit exclusion criteria.

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