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

Annotations only carry negative hints (readOnly=false, idempotent=false, destructive=false), so the description carries the behavioral burden. It discloses ownership ('owned by you'), access behavior ('someone else's private app answers not found'), persistence (read back later via get_app_artifact), and create-vs-patch semantics. This is exactly the kind of context beyond annotations that an agent needs.

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 dense and front-loaded with the core definition, then moves to parameters, usage, and permissions. Every sentence carries information, though the inline '|' separator and the list of examples make it slightly less polished than it could be.

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 7-parameter write tool with no output schema, the description explains the artifact concept, when to create vs patch, and permission behavior. It does not state the return value of the write call, and the 'required when creating' nuance for type is only in the schema, not the description, leaving a small gap.

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. The description adds meaningful parameter semantics: type is a free-form label with examples, spec and/or data may be supplied, and artifact_id toggles create vs patch. It does not add details for visibility or app_id, but the schema already documents those.

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 opens with a specific verb and resource ('Save an ARTIFACT into an app') and then defines what counts as an artifact with concrete examples (Plotly spec, saved report, board, screener view). It also names the read-side counterpart get_app_artifact, so an agent can distinguish writing from reading without opening schema.

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?

It gives explicit when-to-use context: 'Use it right after create_app to seed the app with something real, or whenever a user asks you to save a view.' It also distinguishes create vs patch via artifact_id. It does not enumerate exclusions against other write-like siblings such as create_chart_from_spec or write_rows, but the primary selection context is clear.

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