corymbus_upsert_contact

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

Annotations already indicate this is a mutable operation (readOnlyHint: false), but the description adds a meaningful warning: '⚠️ Écrit dans le CRM de production' (Writes to the production CRM). This flags the side effect of impacting production data, which goes beyond the binary annotation flags. It lacks further detail on irreversibility or permission requirements, but the warning is valuable.

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 a single, concise sentence that front-loads the core operation and includes an essential production-impact warning. Every word earns its place; there is no redundancy or unnecessary detail.

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 14 parameters, no required fields, and no output schema, the description is under-specified. It covers the create/update distinction but omits information about input constraints, validation rules, response format, or error behavior. The agent would need to rely on an incomplete schema and infer the rest, which is risky for a production-mutating tool.

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 21% (3 of 14 properties have descriptions), and the tool description provides no parameter-specific information beyond the already-schema-documented id semantics. Most parameters (email, owner, lastname, extra_fields, etc.) remain undocumented in both schema and description, leaving the agent without guidance on how to populate fields correctly.

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 tool's verb and resource: 'Crée (sans id) ou met à jour (avec id) un contact' (creates or updates a contact). It explicitly distinguishes create vs. update based on presence of 'id', and the resource 'contact' differentiates it from sibling upsert tools for accounts, opportunities, and activities.

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?

The description provides clear usage context by specifying that omitting 'id' creates a contact and providing 'id' updates one. This directly guides the main decision when invoking the tool. However, it does not mention when to prefer alternative tools (e.g., list_contacts for reading, raw_request for custom operations) or exclude inappropriate scenarios.

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