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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real context beyond them: the exact truth condition for verified=true, an explicit statement of what it does NOT assert (Bitcoin status, upstream accuracy), the no-key requirement, and the missing-argument fallback. This is unusually rich behavioral disclosure.

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?

Front-loaded with the core purpose and truth condition, and every sentence carries content (scope limit, return fields, usage, fallback). It is dense with parentheticals and could be tightened, but nothing is clearly 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 no output schema, the description compensates by enumerating the returned JSON fields (row_sha256, merkle_root, row_hash_matches, inclusion_path_reaches_root, verified, proof_url). Combined with scope limits and usage, an agent has everything needed to call and interpret it.

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 the baseline is 3, but the description adds semantic meaning beyond the schema by tying expected_row_sha256 and leaf_index to the verified=true condition and the manifest merkle_root. It reinforces rather than merely repeats the field formats.

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 verb+resource (retained Merkle-membership check for one depin_onchain observation) and scopes it tightly to a single dataset and row, distinguishing it from the sibling verify_value by naming the exact proof type and data domain. An agent can tell what it does without opening the schema.

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 an explicit when ('when you hold a row from a daily batch and want to show it was committed that day'), a when-not ('Other datasets: unsupported'), and even describes missing-argument behavior (lists days with a proof ready plus an example). It does not name a sibling alternative to redirect to, so it stops short of the top bar.

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