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

Annotations already indicate destructive/write behavior (readOnlyHint=false, destructiveHint=true). The description adds substantial transparency: it persists a receipt, requires a write scope, explains that no mutation-result cache stores source content, details timeout recovery, replay semantics, restart behavior, OCR consent, and cautions about untrusted evidence. This far exceeds the minimal annotations and gives agents a clear model of side effects and constraints. No contradiction with 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?

The description is a long, dense block of imperative sentences touching on many peripheral concerns (quoting, exhaustion, untrusted evidence). While the core action is front-loaded, the extra operational advice could be moved to a separate notes section. It is not concise, and the structure could be improved with paragraphs or bullets, but it is not pure tautology.

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?

Given the tool's complexity (7 params, nested objects, no output schema), the description covers the essential workflow and behavioral constraints well: revision iteration, write scope, replay semantics, timeout handling, restart, OCR consent, and evidence caution. It lacks explicit descriptions for some parameters, but the schema provides patterns and the description covers the key semantics. Overall, an agent can likely use 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?

Schema description coverage is only 14% (only projectId has a description). The description compensates partially: it explains expectedReadRevision usage ('begin with null'), refers to sourceKey/contextRevision/readRevision, implies purpose of restart ('Restart explicitly after source changes'), and hints at enableOcr ('OCR requires explicit customer consent'). However, it does not systematically explain each parameter (e.g., pageRevision, contextRevision structure), leaving some gaps that the schema alone does not cover.

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 states a clear verb-resource pair: 'Return a bounded Snipara document page and persist only its receipt.' It distinguishes this from a mere read by emphasizing the receipt persistence, which hints at a distinct operation. However, it does not explicitly compare against siblings like helvabase_read_source_original or helvabase_read_source_excerpt_page, so agents may still be unsure when to pick this one.

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 operational steps (begin with expectedReadRevision=null, then repeat with latest revision, replay semantics) but gives no guidance on when to choose this tool over alternatives. No explicit comparison or 'use this only when...' statements. It does mention when to restart (after source changes), but that is within-tool behavior, not alternative selection.

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