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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real value beyond that: the excerpt is 'frozen' (snapshot semantics), paginated via nextOffset, and explicitly 'untrusted evidence' — a meaningful prompt-injection caution not derivable from annotations.

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?

Three short sentences, front-loaded with the core action and scoping constraint, then pagination, then the trust warning. No filler sentences.

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?

No output schema exists, and the description covers the key return signal (nextOffset) plus the untrusted-content caveat, which is helpful. However, for a 5-parameter tool with a nested required object and 20% schema coverage, the parameter semantics are too thin for an agent to invoke it confidently.

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 only 20% and the description compensates poorly: it never explains marker, the nested draftRevision (outputJobId + payloadHash), or the projectId semantics. 'Bounded page' and 'follow nextOffset' gesture at limit/offset but add no syntax or default guidance beyond the schema.

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 ('read a bounded page of a frozen citation excerpt') and pins the scope to 'the exact draft being reviewed'. It actively distinguishes itself from sibling reads like inspect_original / read_source_original by declaring 'this is not the complete original or a freshness check'.

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 a pagination instruction ('follow nextOffset') and an exclusion ('not the complete original or a freshness check'), which implies when this is the wrong tool. But it never names the sibling to use instead (e.g. inspect_original, read_source_excerpt_page), so routing still requires inference.

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