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

With no annotations, the description carries the full burden, and it does disclose two useful behaviors: the ordering contract and that 'delete' affects future imports and the UI rather than necessarily existing data. It admits uncertainty about how a breach fails ('rejected request? key dropped? contact skipped?') instead of guessing, which is honest but leaves the agent without a definitive failure model, and it says nothing about permissions, uniqueness conflicts, or reversibility of deletion.

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 opening line front-loads the resource definition, and the register-first rule follows immediately. The middle sentence is a slightly rambling meta-comment about what the contract does not specify, and the stray paragraph break inside 'delete' splits a single idea, but overall there is little waste.

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 8-parameter management tool with full schema coverage and an output schema, the description supplies the essential conceptual model (what a custom field is, the registration ordering, deletion scope) that the schema cannot express. It stops short of covering permissions or the effect of deletion on already-stored contact values, which an agent doing destructive cleanup would want.

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; the schema already marks label and field_id as REQUIRED by create/delete and documents the op enum. The description adds conceptual meaning to field_id ('the stable key used inside customFields') but does not restate or enrich the other parameters, notably the _org/_group/_project/_run_id context parameters.

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 names the resource concretely ('custom contact fields — the metadata keys an import may carry') and implies the lifecycle verbs (register, delete), which separates it from minari_contact and minari_list by focusing on field definitions rather than contacts. It never states the full op set (list/create/delete) in one place, leaving the read case implicit.

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 gives a clear precondition — a key must be registered here BEFORE it can appear in `customFields` of an imported contact — which tells the agent when to reach for this tool versus importing directly. It also scopes 'delete' to future imports and the UI. It does not explicitly say when to use 'list' (e.g. to discover valid keys before an import), so the enumeration case is left to inference.

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