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

With no annotations, the description carries the full transparency burden. It discloses key behaviors: it can set or update (implying overwrite), resolves values by field_key, and passing null clears the field. However, it does not mention permission requirements, whether the operation is idempotent, or what happens on invalid entity IDs or field keys. It's better than a bare mutation tool but not fully transparent.

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 compact and front-loaded: the core purpose is in the first sentence, followed by two illustrative examples and a critical caveat (null clears). Every sentence earns its place, and the structure guides the agent from what → when → how.

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?

The tool is a simple setter with no output schema and 100% schema coverage. The description covers the essential context: target entities, examples of use, a prerequisite call, and the null-clearing edge case. It doesn't address error handling or return values, but for this tool's complexity and scope, the description is nearly complete.

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 the baseline is 3. The description goes beyond the schema by giving concrete examples of values ('Hot', '$250k') and explaining that fieldKey resolution depends on the key naming convention (cf.lead_temp). It also reinforces the null-clearing behavior with a specific statement, tying parameter semantics to practical usage.

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-resource pairing: 'Set or update a custom field value on a specific contact, company, or deal.' This clearly distinguishes it from sibling tools like custom_fields_create (which creates field definitions) and custom_fields_list (which lists available keys). The examples make the purpose instantly actionable.

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 description explicitly says 'Use this when' and gives two concrete natural-language triggers (e.g., 'Casey is a Hot lead'), which tells an agent exactly when to invoke it. It also advises calling custom_fields_list first when the field keys are unknown. It doesn't explicitly name alternatives or when-not-to-use cases, but the examples and prerequisite provide strong practical guidance.

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