llm_quality_guard

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

Since no annotations are provided, the description carries the full burden. It discloses the threshold (0.7), the condition ('sufficient samples'), the output format (table with trend arrows and alerts), and the display of rolling averages. This is comprehensive for a simple monitoring tool.

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 extremely concise: two sentences with clear args and returns, no fluff, and front-loaded with the core purpose. Every sentence earns its place.

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 tool with one optional parameter and an output schema, the description is complete. It explains what the tool does, the input, the threshold, the output format, and the condition for alerts. There are no missing elements that would hinder correct invocation.

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 only parameter 'days' is described as 'Number of days of history to analyze (default 7),' which essentially restates the schema (default 7, integer). While the description adds the word 'history', it does not provide additional semantic context beyond the schema. Given the low schema description coverage (0%), the description compensates only marginally.

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 it shows quality scores per model with degradation alerts. It uses specific verbs and resources ('Show quality scores', 'displays rolling average judge scores'), making the purpose clear. However, it does not explicitly differentiate from similar sibling tools like llm_quality_report or llm_model_eval, so it loses a point.

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 over a specified number of days, with alerts for degradation below 0.7. It gives the default value for days, but it does not provide explicit when-not-to-use guidance or mention alternatives among the many llm_* sibling tools.

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