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

Annotations already signal idempotent and destructive behavior, and the description adds concrete context: re-sending an existing list does not duplicate, results include created/updated counts, and null or omitted name/email values clear fields. The only blemish is an internal contradiction between 'Omit to keep the name already stored' and 'leaving one out clears it,' which slightly undermines transparency.

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 main description is three short, front-loaded sentences covering operation, batch size, idempotence, and return value. Every sentence earns its place; the schema descriptions handle the remaining detail.

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 destructive batch operation, the description covers the 500-item cap, externalId matching, created/updated counts, and differentiation from upsert_identity. With annotations and an output schema available, this is nearly complete; the omit/null contradiction is the main gap.

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%, so the baseline is 3, but the added array-level guidance directly contradicts the property-level descriptions: name/email say 'Omit to keep' while the identities description says 'leaving one out clears it.' This makes the actual parameter behavior ambiguous, so the description fails to add reliable meaning 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?

The description opens with a specific verb and resource: 'Creates or updates up to 500 learners in one call.' It also states the matching key (externalId), making the tool's bulk upsert behavior unambiguous and distinguishing it from single-item upsert_identity and bulk_delete_identities.

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 conveys when to use this tool (bulk operations up to 500 learners) and the schema description explicitly contrasts it with upsert_identity: 'Unlike upsert_identity, name and email are written as sent, so leaving one out clears it.' It does not state explicit exclusions or decision rules, but the context is sufficient for an agent to choose this over the sibling upsert tool.

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