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

Annotations cover the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), so the bar is lower. The description still contributes real context the annotations do not: the operation is metered/billed and it hands back a verification id rather than results, which tells the agent this is a paid, asynchronous kick-off rather than a synchronous answer.

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 core action and immediately followed by the return contract. The only minor waste is '(metered)' appearing in both the title and the description body.

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 five-parameter, metered, asynchronous job with no output schema, the description omits the natural next step: that the returned id must be polled via verification_status and read via verification_result. The agent can guess this from the sibling names, but the description does not close the loop.

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 100% and all five parameters carry their own documentation (sample modes, source shape, idempotency_key retry semantics, markdown input). The description adds nothing parameter-level beyond what the schema already states, so the baseline of 3 applies.

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 and resource ('Verify citation-sentence bindings in a document against sources') and adds the return contract ('Returns a verification id'), which implies the async split from the sibling verification_result / verification_status tools. It never names those siblings explicitly, so the differentiation is inferred rather than stated.

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 when-to-use guidance, no exclusion criteria, and no mention of the obvious alternatives (check_source for a single source, verification_result / verification_status for retrieving the outcome). The only usage signal is the parenthetical '(metered)', which hints at cost but not at routing.

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