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

With no annotations, the description carries the full load and does most of it well: 1 CRD per call charged even on rejection, 429 RATE_LIMITED costing nothing, first-touch signup attribution rules, the created:true signal, and request_id in errors for support escalation. It stops short of stating authentication requirements or whether a rejected call partially mutates state, which keeps it off a 5.

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?

Information-dense and front-loaded, with the create/upsert behavior first followed by attribution, cost, and error handling. The opening sentence packs lookup precedence into a parenthetical phrase, which is slightly harder to parse than a clean split, but no sentence is filler.

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 10-parameter mutation tool with no annotations and no output schema, the description covers the costly and surprising behaviors (billing, error identity, attribution side effects, metadata field dropping is covered in schema). It does not describe the shape of the returned user object beyond created:true, which is a minor residual gap given no output schema exists.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: the email-before-external_id dedupe precedence, and the signup_url fallback to the connection's x-app-origin header plus the rule that attribution is only written on new users or users lacking one. These are behavioral semantics the schema cannot express.

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 and resource ('Create an end user') plus the upsert scope ('or return/update the existing one'), and explains the lookup order (email first, then external_id). This tells an agent it can rely on this tool for existing users too, which meaningfully separates it from update_user and bulk_create_users.

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 idempotent email/external_id lookup tells the agent this is safe to call when unsure whether the user already exists. However, it never names alternatives such as bulk_create_users for multiple users or update_user for later modifications, so the agent must infer the boundary.

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