hcm_atom_consume

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

Beyond the readOnlyHint=false annotation, the description discloses that it persists a checkpoint to file store and that dryRun prevents advancement. This gives the agent meaningful insight into side effects, though it omits potential error or concurrency 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 two tight sentences with no filler. Core behavior and the key side effect are front-loaded, making it easy to scan.

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 mutating consume-style tool with no output schema and low parameter coverage, the description leaves gaps around cursor semantics, limit defaults, collection filtering, and when to prefer this over atom_poll. It captures the essence but not enough for confident invocation.

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 only 33% and the description adds no explanation for limit or collection. The mention of 'after cursor' references a concept not present in the parameters, and the effect of limit and collection scope remains undocumented.

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 identifies the action (consume/poll + advance checkpoint) and resource (Atom entries), which differentiates it from list/poll siblings. However, it does not explicitly name an alternative or define where the cursor comes from, leaving minor ambiguity.

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 phrase 'poll + advance checkpoint' implies this tool is used when the caller wants to both read and persist progress, with dryRun as an opt-out. Yet there is no explicit when-to-use versus hcm_atom_poll or hcm_atom_get_checkpoint, nor any exclusion guidance.

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