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

The description asserts 'Writes upsert on (entity_id, field_definition_id) so replaying a batch is idempotent,' which directly conflicts with the structured annotation idempotentHint=false. An agent reasoning about safe retries receives opposite signals from prose and metadata. (The scope requirement and column-dispatch behavior are otherwise useful, but the explicit idempotency conflict governs this score per the rubric.)

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 compact sentences, front-loaded with the action and key, then the column-selection rule, then replay/scope notes. Dense but every clause carries operational content; no wasted preamble.

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?

With no output schema and seven parameters, the description covers the important operational facts an agent needs: natural-key upsert, typed column selection, fallback shim, and required scope. It omits error behavior (unknown field_definition_id, type mismatch) and the response shape, but is otherwise sufficient for calling the tool.

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 the description's mapping of value_text/value_number/value_date/value_boolean to field_type largely restates what each property description already states ('use for field_type=number', etc.), including the ISO format and the precedence rule for the legacy `value` shim. It adds no syntax or constraint information the schema lacks, so the baseline 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?

The opening sentence gives a specific verb and resource — 'Create (upsert) a custom field value for an entity' — and the upsert-on-composite-key detail clarifies the effect. It does not explicitly differentiate itself from the sibling update_custom_field_value or bulk_create, so an agent must infer the division of labor.

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?

It clearly prescribes the preferred call pattern (set the value_* column matching field_type) and offers the legacy `value` shim as the fallback, plus names the required scope. It stops short of stating when to use this versus update_custom_field_value or bulk_create for multi-record writes.

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