search_custom_fields

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

Annotations provide readOnlyHint=true, and the description confirms it returns matching fields. The description also discloses that Type filtering expects the stored base type (not the composite name) — a non-obvious behavioral nuance. It does not detail pagination behavior beyond schema parameters, but the read-only safety profile is already covered by annotations, so no contradiction.

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?

Three sentences, front-loaded with the action and purpose, followed by search dimensions and return values. The description is efficient, though the return-value sentence is slightly redundant with the schema's field descriptions. No wasted words.

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 description is complete for a read-only search tool with 100% schema coverage. It covers why to use it, how to search, return values, and the Type nuance. It doesn't explain pagination defaults, but the schema already defines them. Given no output schema exists, a bit more detail on result ordering or default match behavior could help, but it's adequate.

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%, including per-parameter descriptions. The description still adds value by clarifying the Type filter pitfall (composite names like SelectSingle won't match), and names the default output fields. This exceeds the baseline 3 by providing practical semantic guidance beyond 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?

The description clearly states the verb (Search), the resource (existing custom fields), and the purpose (avoid duplicates before creation). It also specifies search dimensions (Name, Type, LookupType) and return values (IDs, types, descriptions). This differentiates it from sibling tools like create_custom_field and list_custom_field_applications.

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?

Explicitly instructs to use this tool before creating new custom fields to avoid duplicates, and names the searchable fields. It provides clear context on when to use it versus creating new fields, and implicitly distinguishes from application-listing siblings.

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