upsert_contact

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

The description adds real behavior beyond the annotations: HTTP status semantics (201 created vs 200 updated), upsert keying, and the partial-write rule that omitted fields including tags are preserved. One tension: the annotations set idempotentHint=false while 'upsert keyed by' implies repeated identical calls converge on the same state, and the description never resolves which interpretation an agent should trust.

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?

Four short sentences, front-loaded with the create-or-update verb and the keying rule, with zero filler. Each sentence adds a distinct fact (key, status codes, partial-update semantics).

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?

With 9 parameters, a nested custom_fields object, no output schema, and near-zero schema coverage, this mutation tool needs more than four sentences. The key and merge-by-omission behavior are covered well, but nested-object merge semantics and per-field constraints (enum values for stage/channel, maxLengths) remain undocumented on the description side.

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 only 11% (only tags is documented inline), so the description has to carry the load. It explains the two required parameters as a composite key and clarifies that omitted fields are left untouched, but it says nothing about name, email, phone, stage, or — most importantly — whether custom_fields is merged or wholesale replaced.

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?

"Create or update a contact" gives a specific verb pair and resource, and "Upsert keyed by (channel, platform_user_id)" tells an agent exactly which identity determines create-vs-update, which is the crucial distinction from the sibling update_contact. It stops short of naming update_contact as the alternative, so the boundary must still be inferred.

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?

Usage is implied rather than stated: the upsert key implies 'use this when you only have channel + platform_user_id,' and the side-effect note implies repeated calls are safe for partial payloads. There is no explicit when-not guidance and no mention of update_contact, create_tag/tag_contact, or what happens if you have an internal contact id instead.

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