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

With zero annotations, the description carries the full disclosure burden and does so well: it discloses non-obvious pricing behavior, the batched/Merkle tree mechanics, and the HTTP/x402 payment requirement — unusual and critical for correct invocation. It doesn't cover error cases, idempotency, or response format, which slightly prevents a 5, but what it discloses (pricing model, payment path) is exactly the non-obvious behavioral information agents commonly misstep on.

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 sentences, ~50 words, zero redundancy. Each sentence earns its place: (1) what it does + economics, (2) what you get back, (3) cost/payment mechanics. Perfectly front-loaded with the core purpose in the first phrase, 'Anchor a Merkle root...' — the description is tight, scannable, and information-dense.

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 1-parameter, no-output-schema tool with full schema coverage, this description hits every needed context: the operation's purpose, its performance characteristics (cheaper per item), return value expectations (inclusion proofs), and edge-case payment behavior (x402, /pay reference). The 5000-hash limit lives in the schema where it belongs, so nothing material is missing given the tool's simplicity.

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% — the single `hashes` parameter is fully defined with pattern, min/max constraints, and a description. Per rubric, baseline is 3 when schema does the heavy lifting. The description adds contextual value by explaining the batching benefit ('single transaction', 'inclusion proof'), but doesn't add syntax or format details for the parameter itself, which is appropriate since the schema already covers it.

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 uses highly specific language: 'Anchor a Merkle root over many sha256 digests' plus 'far cheaper per item than notarizing each one' clearly identifies the batch operation and differentiates it from the notarize_hash sibling. The title 'Timestamp many hashes in one transaction' reinforces the purpose with a specific verb+resource structure. This stands distinctly apart from siblings like archive_url or verify_hash.

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 phrase 'far cheaper per item than notarizing each one' explicitly positions this tool AGAINST notarize_hash with a cost-based decision criterion — this is a when-to-use/when-not-to-use signal. The mention of 'Each hash gets an inclusion proof' gives the agent a reason to choose this tool (batch cost efficiency) and what value to expect. It never explicitly says 'use for batching, not single hashes,' but the implied tradeoff is unmistakable and actionable.

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