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

Beyond the readOnlyHint=false annotation, the description reveals an important upsert behavior: if an object of the same type and name already exists, it is returned instead of duplicated. It also explains when allow_duplicate should be true and states that the return value includes object_id for follow-up connecting, which is useful in the absence of an output schema.

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?

Each of the four sentences serves a distinct purpose: stating the core action, giving the usage trigger with examples, explaining dedup/allow_duplicate behavior, and describing the return value. There is no redundant filler or repetition of schema content, and the most important scoping information is front-loaded.

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?

Given there is no output schema, the description's note that the tool returns the object with its object_id is essential and covers the key return contract. It also addresses deduplication, the allowed object types, and the allow_duplicate edge case, while the schema handles field-level details. For a create tool of this complexity, nothing critical is missing.

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?

Since schema description coverage is 100%, the schema already documents all seven parameters, setting the baseline at 3. The description adds meaningful semantics for allow_duplicate ('only when the user confirms they want a second one') and for the dedup condition tied to type and name, which helps an agent decide parameter values beyond the schema descriptions.

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 states a specific verb ('Create') and a specific resource ('object in the user's graph'), then enumerates the kinds of objects it covers (project, note, fact, web link, etc.). This clearly distinguishes it from sibling create_* tools like create_calendar_event, create_gmail_draft, and create_tracker, which target different resource types.

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 explicitly says 'Use when they ask to add something' and lists the supported object types, giving a clear trigger for invocation. It also provides conditional guidance for allow_duplicate, but it does not explicitly name sibling alternatives such as search_graph_objects for finding existing objects, so it stops short of full when-not-to-use guidance.

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