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

With no annotations, the description carries the full burden and it does well: it gives the exact truth conditions ('verified=true ONLY when ... AND ...'), defines the leaf index and row hash, and flags what the result does not certify. It stops short of describing the full response/error shape, so it is not a 5.

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, no filler and no restating of the tool name. The main purpose and parameters are front-loaded, and each clause (format, row path, AND condition, limitations) earns its place.

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 4-parameter verification tool with no annotations and no output schema, the description covers inputs, verification semantics, dataset restrictions, and interpretation caveats. The only mild gap is that it doesn't explicitly state the output container for verified (e.g., a boolean field), though it is strongly implied by 'verified=true.'

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?

Even though schema description coverage is 0%, the description defines every input's meaning: stamp_day's format, leaf_index's 0-based row location in '/attestations/batch_<day>.tsv', and expected_row_sha256's role in the hash check. It also ties dataset to the only supported value, depin_onchain.

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 concrete verb and resource: 'Retained Merkle-membership check' for 'one depin_onchain observation', which immediately identifies its role. It also distinguishes itself from broader provenance/ledger tools by stating it verifies inclusion only and 'says nothing about Bitcoin status or upstream accuracy.'

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 states the supported dataset and explicitly excludes others: 'Other datasets: unsupported (no retained proof).' The limitation 'Says nothing about Bitcoin status or upstream accuracy' also tells the agent when not to rely on this tool's result. It does not name a specific sibling alternative, but the exclusion is clear enough.

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