Cache a rule extraction back onto a container

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

With no annotations, the description carries the full burden. It discloses important behavioral traits: it overwrites cached rules? Actually it says 'Rules a user wrote by hand are never overwritten,' which implies it may overwrite machine-generated rules. It also warns that a narrow extraction is worse than none, and specifies the format (one imperative rule per line, drop background/explanation, keep code examples and links). This is rich behavioral context 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 a single dense paragraph, front-loaded with the trigger condition and the core action. It packs a lot of important guidance (completeness, format, preservation of hand-written rules) without excessive verbosity. Slightly long but every sentence 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?

For a write tool with no annotations and no output schema, the description covers the key context: when to use, what to extract, how to format, and what not to overwrite. It doesn't describe the return value or error cases, but those are less critical for an agent deciding to call it. The main gap is not stating whether the tool overwrites existing machine-generated rules, though the hand-written rule caveat implies it.

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 50%: the 'rules' parameter is described as 'One imperative rule per line, task-agnostic,' and the description reinforces that with format and content guidance. The 'container_id' parameter has no description in the schema, but the description implies it identifies the container to write back to. The description adds meaningful semantics for the rules parameter and enough context for container_id.

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 clearly states the action: after reading a container with no cached rules, distil it and save the result. It names the resource (a container) and the specific operation (caching extracted rules), and it distinguishes itself from siblings by describing a write-back workflow that follows reading.

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 when to use this tool: after reading a container whose result said it has no cached rules. It also gives a strong exclusion: do not use it for narrow, task-specific extraction; extract every actionable rule. This is clear guidance for an agent deciding between this and sibling read/search tools.

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