Build an evaluation test set from real conversations

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

With no annotations provided, the description carries the burden and does disclose the key side effect: 'Read-only apart from writing the file.' It also reveals the data source (real sessions), the ordering (most frequent first), and the semantics of onlyFailed as a filter for escalation/unanswered/abandoned sessions. It does not address auth prerequisites or volume/latency, but it is materially more informative than a bare mutation statement.

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 tight sentences, front-loaded with the verb and artifact, then the filtering rule, then the workflow handoff. No filler and nothing repeated from the schema.

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 10-parameter, all-defaulted CSV-generation tool with no output schema, the description covers the data source, filter behavior, ordering, write side effect, and the follow-up tool. It could say more about auth/setup prerequisites, but the required workflow context is present.

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 100%, so the schema already documents all ten parameters and the baseline is 3. The description adds only the 'most frequent first' ordering (relevant to top/maxCases) and a rationale for onlyFailed, but gives no extra syntax or format detail beyond the schema.

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?

States a concrete verb and output artifact: 'Write the portal's import CSV from questions people actually asked, most frequent first.' It also implicitly distinguishes itself from the workspace-guessing path ('instead of guessing from the workspace'), which maps to the cs_create_test_set_csv sibling, though it never names that sibling directly.

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?

Gives clear context (build a test set from real transcripts, filter with onlyFailed) and names the downstream step explicitly: 'import it once in the portal, then cs_run_evaluation automates the runs.' It stops short of stating when NOT to use this (e.g. when cs_create_test_set_csv is preferred), so it is context-rich but not exclusive.

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