create_project_user

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

Annotations declare destructiveHint=true and idempotentHint=false, which is non-obvious for a "link" operation, yet the description says nothing about what gets destroyed, whether re-adding an existing member errors, or what permissions are needed. The one behavioural note (JSON-encoded string fields must remain strings) is obscure and doesn't map to any visible parameter.

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?

It is short and front-loaded with the core action, which is good. However, the third sentence about JSON-encoded string fields is cryptic in a schema whose only string field is a free-form role, so that sentence does not clearly earn its place.

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 destructive, non-idempotent, open-world mutation with a nested body object and no output schema, the description omits membership semantics, role validity, error behaviour, and prerequisites. An agent could parse it but would likely call it with an incorrect or underspecified body.

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 0% and the description does not name the nested body fields role or user_id, nor explain valid role values or how they are obtained. The vague instruction to "supply API fields in body" leaves the agent to guess the required body shape from the raw schema.

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?

"Link user to project" states a specific verb and resource, and separates it from update_project_user and delete_project_user. The added endpoint reference (POST /project/{project_id}/users) reinforces the create semantics, but it never names the sibling tools it should be chosen over.

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?

There is no guidance on when to use this versus update_project_user (existing membership) or create_user (user does not exist yet). The only instruction is a mechanical note about supplying body fields, which is invocation mechanics rather than usage context.

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