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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false. The description goes meaningfully beyond them by disclosing transaction semantics ('All-or-nothing: if any value fails validation or access checks, no values are saved') and the existence of access checks, which the annotations do not convey. It stops short of describing what happens to pre-existing values on upsert or the response shape.

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 tight sentences with zero filler: capability and limit first, the critical failure semantic second, the use case last. Nothing is repeated from the schema or annotations.

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 1-parameter mutation with no output schema and annotations covering the safety profile, the description supplies the limit, atomicity guarantee, failure condition, and a representative use case. The remaining gap is the per-item field structure and enum, which an agent must read from the schema.

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 array parameter, so the description carries some burden. It contributes the 50-item cap and the fact that items are keyed values, but says nothing about the item structure (fieldId, entityId, entityType enum, nullable value), leaving the enum and entity scoping undocumented anywhere.

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+resource ('Upsert ... custom field values') plus batch scope ('up to 50 ... in one call'), which implicitly distinguishes it from the singular set_custom_field_value sibling. It never names that sibling explicitly, so the differentiation is inferred from the batch/limit framing 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?

The final sentence gives one concrete context ('batch-populating fields on a set of imported tasks'), which implies when to reach for it over the single-value tool. There are no exclusions, prerequisites, or explicit alternative named, so an agent must infer the boundary itself.

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