verify_external_proof

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes beyond these by revealing that it does not interact with the local stamp store, that paths must pass a whitelist, that size caps apply per input, and crucially it clarifies the epistemic scope of a confirmed result (proves existence before a block, but not authorship or content truth). This adds meaningful behavioral context beyond the annotation flags, and there is no contradiction.

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 information-dense with zero filler. It front-loads the core action, then packs constraints, non-behaviors, and proof semantics into a single compact block. Every sentence contributes unique, useful detail—none are redundant with the schema or annotations. The structure is logical: what it does, what constraints apply, what it does not do, and what the result means.

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 two-parameter verification tool with full schema coverage and safety annotations, the description is nearly complete. It explains the inputs, the validation constraints, the tool's side-effect-free nature, and the meaning of a confirmed result. It does not explicitly describe the return value or error behavior, but given there is no output schema and the tool is read-only/idempotent, this is a minor gap. Overall, an agent has sufficient information to call it correctly.

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?

Both parameters have schema descriptions that explain their meaning ('Path to the exact file covered by the proof' and 'Path to the corresponding .ots proof file'), so schema coverage is 100%. The description adds value by attaching specific constraints to each parameter: the covered file is subject to the preservation size cap and the proof file has a separate 1 MiB cap. This parameter-level context is not in the schema and helps the agent validate inputs before calling.

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 precise verb-resource pairing: 'Verifies an external OpenTimestamps .ots file against its covered local file.' It clearly identifies the action (verifies), the resource (external .ots file against a local file), and the scoping 'external' distinguishes it from sibling tools like verify_timestamp. The explicit mention that it does not touch the local stamp store further reinforces its distinct purpose.

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 provides clear contextual guidance by specifying constraints (directory whitelist, size caps) and stating what the tool does not do (read/modify the local stamp store), which implies when it is appropriate to use. However, it does not explicitly name an alternative or state 'use this when...', so it stops short of a full when/when-not directive. The context is strong enough that an agent can infer the right selection among siblings.

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