rws_metrics_append

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

Annotations already declare idempotentHint=true and destructiveHint=false, so the description's dedup/no-overwrite sentence mostly corroborates structured data rather than adding new information. The genuinely additive part is the write-conflict stance ("conflicting values never overwrite") and the pinned-contract constraint, but nothing is said about expectedRevision conflicts, batch limits, or error behavior on mismatch.

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?

Three short sentences, front-loaded with the action and resource, then the dedup semantics, then the exclusion. No filler and no repetition of the tool name.

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 six-parameter mutation tool with nested objects, an optimistic-concurrency token, and no output schema, the description is thin. It omits what expectedRevision enforces, what requestId deduplicates, and what the response returns, leaving an agent unable to call it correctly without inferring from raw schema 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?

Schema description coverage is 0% across six parameters, including a nested runRef object, requestId, and expectedRevision, so the description must carry the explanatory burden and does not. "In batches" loosely gestures at the points array, but expectedRevision (optimistic concurrency), requestId (idempotency key), and runRef's version field are entirely unexplained.

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?

A specific verb+resource: "Append actual process measurements in batches" scoped to "the run's pinned processMetrics contract," which cleanly separates it from the read-side siblings rws_metrics_query and rws_metrics_snapshot. The closing "Does not run a model" adds a negative boundary, though no sibling is named 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?

Usage is implied (write measurements into an existing run) and one exclusion is stated (it does not execute a model), but the description never routes the agent among its close siblings rws_metrics_snapshot and rws_metrics_query, nor states prerequisites such as the run needing to exist.

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