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

Despite annotations covering the basic safety profile, the description adds substantial behavioral detail: where data lands (Private under subheadings when runtime updates are enabled), what is preserved (structured metadata like suggested prompts, categories, tags), what could change it (another structured write path), and the confirmation gate. This goes well beyond what readOnlyHint/destructiveHint convey and gives the agent a realistic model of the write behavior.

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 long but dense, with every sentence earning its place: core action, exclusions, optional runtime behavior, metadata preservation, confirmation requirement, and content restrictions each occupy one distinct sentence. The core action is front-loaded in the first sentence, and while there is some redundancy in the confirmation requirement (mentioned in both description and schema), the efficiency is strong given the guidance load.

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 complex write tool with 7 parameters, the description is complete: it covers intended use, exclusions, data placement, preservation semantics, confirmation requirements, and sensitive-content prohibitions. The output schema exists so return values need not be described, and nothing an agent needs to decide whether and how to invoke this tool 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?

Schema coverage is 100%, setting a baseline of 3, and the description does add value beyond the schema: it clarifies that contextId must be the latest mutable draft, that feedback must represent durable repeated corrections rather than one-off details, and reinforces the confirmed gate. The description frames the intended use of the parameters even though it doesn't describe each parameter's syntax.

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 first sentence states a specific verb (save), resource (active private Context draft), and scope (single latest Context), clearly distinguishing it from the sibling oi.brain.save-feedback. It further differentiates itself by explicitly excluding multi-context selectors and version-pinned Contexts, so an agent can tell it apart from the broader contexts family without opening schemas.

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 gives explicit when-to-use and when-not-to-use guidance: only after user confirmation, only for repeated corrections or updated logic, never for one-off details, temporary debugging, secrets, or credentials. It also names exclusions (multi-context selectors, version-pinned Contexts) and notes an alternative path for structured metadata updates, leaving little to inference.

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