Fields: get

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one useful content-scope fact, that relationship configuration is included in the returned definition, but says nothing about failure cases (unknown entity/field) or any auth requirements.

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?

A single sentence with zero filler, and the scope-defining phrase ('one field') plus the differentiating detail ('including relationship config') are both front-loaded.

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 simple two-parameter read tool whose schema and annotations are fully populated, the description is adequate; the extra note about relationship config is the main value-add. It would be complete if it hinted at what happens when the field or entity does not exist.

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 coverage is 100% with two documented string parameters, so the baseline is 3. The description adds no syntax, naming-convention, or format detail for entity or field_name beyond what the schema already states.

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 concrete verb+resource ('Get the full definition of one field') and scopes it to a single field, which implicitly separates it from fields_list. It also flags that the payload includes relationship config, so the agent knows this is the deep-detail read rather than a summary. It stops short of naming siblings explicitly.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as fields_list or entities_get. The agent must infer that 'one field' means use this instead of the list tool.

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