llm_quality_guard

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

With no annotations, the description carries full burden. It discloses the tool is read-only (shows scores), returns a formatted table, and describes alert conditions. It could mention side effects or rate limits, but for a read-only tool it is adequate.

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 six lines including Args and Returns, with no unnecessary words. It front-loads the purpose and immediately provides actionable details.

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?

Given the tool's simplicity (one parameter, no annotations, output schema exists), the description covers purpose, input, output format (table with scores, trend arrows, alerts), and alert conditions. It is complete.

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%, but the description documents the sole parameter 'days' with its meaning ('Number of days of history to analyze') and default. This adds value 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 states 'Show quality scores per model with degradation alerts (v6.2)'. It provides a specific verb ('Show') and resource ('quality scores per model'), and distinguishes from siblings like 'llm_quality_report' by focusing on degradation alerts and rolling averages.

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 explains the tool displays scores and alerts when a model's score drops below 0.7 with sufficient samples. While it implies monitoring use, it does not explicitly contrast with alternatives like 'llm_quality_report' or 'llm_dashboard'.

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