llm_quality_guard

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

With no annotations, the description discloses key behaviors: rolling average calculation, alert threshold (<0.7) with sufficient samples, and output format (table with trend arrows). It lacks details on what constitutes 'sufficient samples' but is otherwise transparent.

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?

The description is four sentences plus Args/Returns, front-loading the main purpose. Every sentence provides value with no redundancy.

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 simple read-only monitoring tool, the description covers purpose, parameters, alerts, and return structure. Minor gap: 'sufficient samples' is not quantified, but overall complete given the output schema exists.

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 schema has 0% description coverage, so the description must compensate. It clearly explains the only parameter 'days' as 'Number of days of history to analyze (default 7)', adding meaning beyond the schema's type and default.

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 clearly states the tool shows quality scores per model with degradation alerts, specifying rolling average judge scores and an alert threshold of 0.7. It distinguishes itself from sibling tools like llm_quality_report and llm_model_eval by focusing on degradation detection and trend arrows.

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?

The description implies usage for monitoring model quality with degradation alerts but does not provide explicit guidance on when not to use it or alternatives. No exclusions or sibling comparisons are mentioned.

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