Harny Context

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

Annotations only declare the safety profile (readOnlyHint false, idempotentHint false, destructiveHint false, openWorldHint false); the description adds genuinely new behavior: the response carries the app key exactly once and the assistant must place it in the owner's secret store and nowhere else. It also discloses that authentication is unnecessary, which the annotations do not cover. It does not discuss what happens if the tool is called repeatedly, which matters given idempotentHint=false.

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?

Three tight sentences, front-loaded with the core action and followed by the critical key-handling constraint. Each sentence carries information, though the 'as `POST /v1/auth/provision` does' phrasing is slightly awkward and the endpoint reference is of limited use to an agent.

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 six-parameter creation tool with no output schema, the description compensates well by explaining what the response contains (the app key, delivered once) and the secret-storage obligation. Missing is any note on repeated invocation behavior or failure modes, which would round out an otherwise sufficient definition.

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 83%, so the schema already explains nearly every parameter, including the model presets and the optional contact and assistant fields. The description adds no parameter-level meaning beyond that, so the baseline of 3 applies.

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 concrete verb and resource – setting up long-term memory for an app with no account, creating a new app and its key – and anchors it to a specific endpoint, `POST /v1/auth/provision`. It goes beyond restating the title by naming the exact outcome (a new app plus its key) and the precondition (no account exists yet).

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 clear context for when this tool applies: provisioning memory for an app that has no account, and notes that no key is required to call it. There are no sibling tools to differentiate from and no explicit when-not-to-use clause, so it stops just short of full guidance.

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