get_results

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

Annotations already declare readOnly, idempotent, non-destructive, and openWorld=false. The description adds genuine domain semantics beyond that: gate meanings and the stale=true condition (case changed after this run). It still lacks permission, error, and return-format context, so it is a modest addition rather than rich behavioral disclosure.

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 terse lines, front-loaded with the payload and the stale caveat, with no filler. Jargon density is high but the text is not padded.

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?

With no output schema and 0% schema descriptions, the description must carry both return shape and parameter meaning. It partly does (gates, stale) but omits case_id, language, and output structure, which is incomplete for a three-parameter tool in a dense sibling namespace.

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 three parameters. The description explains run_id optionality ('latest or given') but says nothing about the required case_id or the ja/en/zh language enum, leaving most parameter meaning 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 names the returned artifacts (run key numbers, ran/converged gates, third gate via gates.verified_by, verification line) so an agent knows roughly what it retrieves. However, the verb is implicit, 'Key numbers' is vague, and it does not distinguish this from siblings such as probe_results, compare_runs, or check_convergence.

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 guidance is given on when to call this versus probe_results, compare_runs, check_convergence, or verify_case, despite a crowded sibling set. Only the parenthetical 'latest (or given)' implies the run_id default, and no exclusions or prerequisites are stated.

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