Create or Update Contact by Contact Person Email

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

Annotations already declare readOnly=false, openWorld=true, destructiveHint=false, so the safety profile is covered; the description adds real behavior: match scope includes main and additional contact persons, only non-archived records are considered, and ambiguity yields a 409. It does not say whether unlisted fields are preserved or cleared on update, nor what is returned — meaningful gaps for an upsert.

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?

Front-loaded with a bulleted decision table that is easy to scan, and every branch earns its place. The opening sentence largely restates the title, a small redundancy.

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 single-body-parameter but deeply nested mutation with no output schema, the description covers the decisive logic (create vs update vs conflict) that the schema cannot. It leaves open the response shape and whether omitted fields are overwritten, which an agent would still want to know.

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 reported as 0%, so the description must carry weight; it does explain that the submitted email is the identity key, which is genuine added meaning. Beyond that it says nothing about the nested contact/contactPerson fields, partial-update semantics, or custom property handling, so it only partially compensates.

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?

States a specific verb pair (create or update) and resource (contact), plus the exact key that decides which happens (contact person email). The three-branch rule set makes it unmistakably distinct from siblings like create_contact, update_contact, and create_contact_person.

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?

Gives explicit conditions for creation, update, and failure (409 Conflict on multiple matches), and clarifies that additional contact persons count in the match. It stops short of naming when to prefer the sibling tools (e.g. create_contact, update_contact_person) instead of this upsert.

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