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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new behavioral facts: the operation is deterministic, no model is involved, and it returns hashes, locations and independent verification instructions — exactly the kind of context annotations cannot express. It stops short of stating limits such as the 50-evidence cap or error behavior on unknown ids.

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?

Two tight sentences, front-loaded with the input condition and output contract, with no redundant phrasing. Every clause carries information an agent needs.

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 does the work of describing the return payload (state, hash, location, independent verification path), and annotations cover the safety profile. It is nearly complete, losing only the evidence-count ceiling and any statement about failure modes for invalid ids.

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 50%: asset_id is well documented with its three id formats, while evidence_ids carries no description. The description partially compensates by framing evidence_ids as the evidence a claim rests on and by describing how they are combined (weakest-link), but it never mentions the minItems/maxItems bounds or ordering expectations.

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 names a specific verb+resource ('verify a claim') and adds real semantic detail — it explains the aggregation rule ('the state the claim earns (the weakest among them)') and the returned artifacts. That is far more than a restatement of the title, though it never explicitly contrasts itself with siblings like ruthven_get_evidence or ruthven_get_proof.

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?

Usage is implied rather than stated: 'Given the evidence ids a claim rests on' sketches the precondition for calling it, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g. use get_evidence for a single record). An agent must infer the routing decision from the description alone.

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