hcm_atom_get_checkpoint

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

The readOnlyHint annotation already declares this a safe read, and the description adds one genuinely useful behavioral detail beyond it: the operation reads a local store rather than a remote CDC source. It does not disclose what happens when no checkpoint exists, whether the local store is auto-initialized, or how checkpoints relate to consumed entries, but the annotation lowers the bar and the local-store context earns some credit.

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?

At eight words the description is tightly written and front-loads the verb and resource. However, the brevity comes at the expense of the parameter and usage context, so it reads as under-specification rather than effective conciseness — appropriate in size but incomplete in content.

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?

Despite the tool's low structural complexity (one optional parameter, no output schema), essential context is missing: the meaning of `collection`, the semantics of a CDC 'checkpoint,' and how this tool fits with hcm_atom_reset_checkpoint and the poll/consume flow. An agent without prior domain knowledge cannot reliably invoke it correctly from this definition alone.

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?

The sole parameter `collection` has zero schema description coverage (0%) and is never mentioned in the tool description, so nothing compensates for the schema's silence. The agent cannot determine whether `collection` is a feed name, a checkpoint key, or an optional filter, nor what omitting this non-required parameter yields. This is a blocking gap for correct invocation.

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 ('Get') and resource ('Atom CDC checkpoint(s)') with a location qualifier ('from local store'), so the core operation is understandable. However, the plural '(s)' and the unexpanded 'CDC' leave ambiguity about exactly what is returned, and it does not differentiate this read tool from its many atom siblings like hcm_atom_poll, hcm_atom_consume, or hcm_atom_reset_checkpoint.

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?

No guidance is given on when to call this tool versus the closely related atom tools — hcm_atom_poll, hcm_atom_consume, hcm_atom_reset_checkpoint, hcm_list_atom_feeds — which the extensive sibling list makes highly relevant. There is no stated use case, prerequisite, or when-not-to-use advice, so an agent must infer the checkpoint's role in the CDC flow.

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