Register immutable evaluation protocols by defining metrics, preprocessing, aggregation, and missing-data policy for reproducible research records.
Register immutable evaluation metric definitions, preprocessing, aggregation and missing-data policy.
| Name | Required | Description | Default |
|---|---|---|---|
| record | Yes | ||
| projectId | Yes | ||
| requestId | Yes | ||
| expectedRevision | Yes |
Changes observed during successful MCP inspections.
v0.3.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already state write, non-destructive, idempotent, closed-world. The description adds one genuinely useful behavioral fact — the registration is immutable — which implies retries are safe but edits require a new record/amendment. It stops short of stating conflict or concurrency behavior despite requiring expectedRevision.
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?
A single front-loaded clause with no filler or redundancy. It is efficient, though its brevity is partly under-specification rather than pure tightness.
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 nested, 4-required-param mutation with zero schema descriptions and no output schema, the description is too thin: it omits revision/conflict semantics, error behavior on duplicate ids, and how the nested metric objects are shaped. Immutability alone does not give an agent enough to call this correctly.
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 0% across 4 required top-level params and a deeply nested record. The sentence echoes the record sub-fields (metrics, preprocessing, aggregation, missingPolicy) but says nothing about requestId, projectId, or the required expectedRevision optimistic-concurrency token, which is the parameter most likely to cause failure.
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?
Names a specific verb ('Register') and a specific resource (evaluation metric/protocol definitions, with preprocessing, aggregation and missing-data policy). That is clearly distinct from siblings like rws_dataset_register or rws_code_register, though it never says so explicitly.
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 when-to-use guidance, no prerequisites, no alternatives. The 'immutable' wording hints that once registered a revision is frozen, but the caller gets no instruction on when this tool is the right choice versus, e.g., rws_amendment_propose or rws_spec_save.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.