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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=true, so the safety profile is covered and the description doesn't need to repeat it. The description does add a behavioral trait the annotations cannot: the tool walks from a claim outward to linked records and sources. What it omits is whether the traversal is transitive or one level deep, whether results are paginated or size-limited, and whether missing evidence yields an empty set or an error — all material for a chain-following call.

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?

A single well-formed sentence with no filler, and the operative element (the claim) is front-loaded. It is arguably too terse for the amount of behavior it is compressing, but nothing written is 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 is the only place return values can be explained, and it gestures at them ('definitive bibliography records and primary or supporting sources') without saying what the response actually contains — record identifiers, both source tiers, or a resolved chain. For a single-parameter read tool with rich annotations this is close to adequate, but the return-shape and traversal-depth gaps matter for a 'trace' operation.

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 description coverage is 0% for the single parameter, so the description must carry the burden of explaining claim_id, and it says nothing about it. It doesn't mention the required 'cp-claim-' prefix enforced by the pattern, nor what an invalid or unknown claim id produces. The schema's regex gives structural hints, but the description adds no semantic meaning.

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 verb 'follow' plus the object 'a preservation claim ... to bibliography records and sources' conveys a traversal/aggregation operation, which is meaningfully different from the record-fetch siblings. However, 'definitive bibliography records' and 'primary or supporting sources' are domain jargon, and the description never states plainly that it returns the evidence graph/chain for a claim rather than a single document. An agent can guess the purpose but cannot crisply contrast it with get_claim or get_citation.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative even though get_claim, get_citation, and get_document all overlap with this space. The only hint is implicit: you need a claim, then you trace it. That leaves the agent to infer whether trace_evidence is a superset of get_claim or a follow-up call.

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