emu_publish_cmr

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it is nearly bare. 'Immediately' usefully implies the operation is synchronous/forced relative to a buffered default, which is a genuine behavioral signal, but there is no disclosure about idempotency, side effects, reversibility, or what happens when there is nothing pending. For a mutation-style operation, this is thin.

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?

Six words, front-loaded, zero wasted modifiers. For a tool with no parameters and no output schema, the brevity is arguably appropriate. It loses a point because the freed-up budget could have bought a short parenthetical (e.g., 'push all pending CMR records now') to disambiguate 'flush.'

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 an annotation-less, param-less tool with no output schema, the description is the only contract, and it's insufficient. A model cannot tell what the call returns, whether it's safe to invoke repeatedly, what state must exist first, or whether 'flush' might be destructive. Compared to the MID example (update_drive), which at least listed its fields, this leaves more open than it closes.

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 tool declares zero parameters, so there is nothing for the description to document — the schema is trivially complete at 100% coverage. Per the rubric, zero parameters earns a baseline of 4, and the description doesn't mislead about any parameters.

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?

'Flush the CMR publisher' pairs a concrete imperative with a specific resource ('CMR publisher'), and 'immediately' adds temporal scope. However, 'flush' is ambiguous between 'force-publish buffered records' and 'discard/reset,' and a model cannot disambiguate from the text alone. It also doesn't clearly distinguish itself from emu_get_cmr_publisher / emu_update_cmr_publisher beyond the generic 'publish' semantic.

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?

There is zero guidance on when to call this tool versus alternatives. The description never mentions emu_get_cmr_publisher, emu_update_cmr_publisher, or the parallel emu_publish_cdr/emu_publish_syslog family, nor any preconditions (e.g., pending records must exist). In contrast to the get_calls high-bar example, no exclusion or routing information is provided.

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