Add a field to an object

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

Beyond the annotations it discloses the non-obvious operational constraints: the key is derived from the label unless supplied, must be unique on the object, and repeat calls with the same key fail; AI columns consume credits and only certain types support ai_prompt. It even names the return shape, structuredContent {field:{field_id, key, label, type}}, so the agent knows what comes back.

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 core action and required inputs are front-loaded, and each subsequent clause adds a distinct constraint rather than repeating the schema. It is a dense single block, though, and could be split into a short usage sentence plus a constraints list for easier scanning.

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 an 11-parameter mutation tool with an output schema, the description covers the decision points an agent needs: which object types, when schema_id is needed, when options is needed, how the key is derived and what happens on collision, and what the response contains. Nothing material for correct invocation is missing.

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, and the description earns more by documenting cross-parameter conditionals the schema does not: options is required for select/multiSelect, schema_id is required when object_type is "custom", and key derivation rules tie key to label. Secondary parameters such as hidden, required, visibility and description are left entirely to 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?

"Adds one field (column) to an object" gives a specific verb and resource, and then enumerates the valid targets (companies, people, deals, custom objects) and the required shape (object_type + schema_id for custom). It also scopes the operation by excluding relationship fields, so an agent can distinguish this from field-editing and record-level tools at a glance.

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 states when the tool applies and several when-not cases: relationship fields must be created in the Heliyos web app, and backfilling existing records with an AI prompt is started from the web app, not here. It does not explicitly route to heliyos_fields_update for modifying an existing field, which is the one obvious disambiguation left implicit.

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