Show Custom Field Metadatum

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

Annotations already declare readOnlyHint and idempotentHint, so the description doesn't need to emphasize safety. It adds useful behavior: company_id defaults to config value when omitted, errors return HTTP status codes (401/403/404), and returns a single JSON object. This goes beyond the annotations, though the company_id default conflicts with the required schema, which slightly undermines 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 well-organized: first sentence gives purpose, then usage condition, then parameter behavioral details, return type, safety note, error semantics, required params, and endpoint. It is dense but not bloated, and all sentences contribute useful context. The inclusion of the full endpoint is slightly redundant but not harmful.

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 read-only fetch tool with an output schema absent, the description covers the essential aspects: purpose, parameter prerequisites, return format, and error cases. It does not discuss the optional 'view' parameter, but the schema fully documents it. The only concern is the company_id contradiction mentioned under parameter semantics, which prevents a perfect score.

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 description doesn't need to restate params. It does add meaning for id (must resolve existing record) and claims a default for company_id, but that claim contradicts the schema's 'required' field. This could mislead an agent into omitting a required parameter, so it detracts rather than adds value.

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 clearly states it returns the details for a specific Custom Field Metadatum, using a specific verb and resource. It distinguishes itself from list tools by indicating it is for when you already know which metadatum you need, and it refers to resolving the id with the matching list tool. This differentiates it from sibling tools like list_custom_field_metadata_company.

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 explicitly says 'Use this when you already know which custom field metadatum you want' and adds that you should resolve id with the matching list tool first, implying when you don't know the id you should use list. It also notes the company_id default behavior and provides context about errors. This provides clear when-to-use guidance.

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