keel_create_policy

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

With no annotations provided, the description carries the full behavioral burden. It discloses what the tool returns (id, key, title), explains the key derivation rule, and reveals the important idempotent/upsert-like behavior that reusing a key targets an existing policy. It could go further by clarifying whether updating replaces or merges the existing policy, but it provides meaningful behavior beyond the 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?

The description is two sentences with no filler. The primary action is front-loaded, and the second sentence delivers the most important caveat about key reuse. Every clause earns 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?

Given there is no output schema and no annotations, the description compensates by stating the return fields and the key identity rule. The input schema fully documents all parameters, including the markdown/description fallback and fields limits. It is not exhaustive about permissions or exact update semantics, but it is sufficient for an agent to invoke the tool correctly in most cases.

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 genuine value by clarifying the key parameter: it is derived from the title when omitted, and because policies are identified by key, reusing one targets the existing policy. This is substantive semantic information not present in the schema alone.

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 and resource, 'Create a policy from Markdown', and clearly separates this from the read-only list_policies and other create_* siblings by naming the policy resource. It also adds the key-reuse behavior that makes the operation more than a plain create.

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 implies when to use the tool: when a policy should be created from Markdown. However, it does not explicitly name alternatives or state when not to use it, such as when merely listing or deleting policies. The sibling tools are all distinct resources, so the usage context is inferable but not explicitly guided.

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