Update Custom Field Definition

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

The description adds substantial behavioral context beyond annotations: partial update behavior, payload nesting ('nested under custom_field_definition'), default company_id behavior, return value ('Returns the modified custom field definition on success'), and error details (401/403/404). It aligns with annotations (readOnlyHint=false, idempotentHint=true) and does not contradict them. This exceeds the bar for 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 description is dense but efficient. Every sentence adds essential value: update scope, partial update behavior, payload nesting, id resolution prerequisite, default company_id, return value, failure modes, required params, and API reference. It is front-loaded with the core purpose and structured logically from behavior to errors to prerequisites.

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 tool with 10 parameters, no output schema, and only basic annotations, the description is remarkably complete. It covers update semantics, partial updates, argument passing, defaults, id resolution via list tool, return value, common error codes, required params, and even the API permissions context ('Company Admin > Custom - Configurable Tools'). An agent has everything needed to call this tool correctly.

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%, so baseline is 3. The description adds valuable semantics: 'Pass the record's fields as top-level arguments — they are nested under custom_field_definition in the request payload for you' clarifies how parameters should be passed, and 'company_id defaults to the value set by procore_set_config when omitted' adds meaning not in the schema. It also highlights required parameters, but the schema already documents each parameter's meaning, so the added value is moderate.

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: 'Updates an existing custom field definition for the specified Procore company.' It clearly distinguishes from create/delete/show siblings by stating 'existing' and mentioning partial update semantics. The scope (company-level) and the PATCH endpoint further clarify the tool's unique role.

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?

Provides clear context: 'Send only the fields you intend to change; omitted fields keep their current values' and 'id must identify an existing parent record — resolve it with the matching list tool first.' It also notes the company_id default from procore_set_config. However, it does not explicitly name alternative tools (e.g., create_custom_field_definitions) or state when not to use this tool, stopping short of a 5.

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