inspect_quality

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

No annotations are provided, so the description must disclose behavioral traits. It only describes what is returned but does not mention read-only nature, data freshness, rate limits, authentication requirements, or any side effects. The description lacks transparency beyond the return schema.

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?

Two sentences: the first clearly states what the tool returns, the second provides a concrete example. No redundant words, all information is essential.

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?

The description lists the output components (average score, sample count, findings/judge breakdown, escalation rate) without an output schema, providing a good overview. It lacks details on output format (e.g., list vs. table) but is largely sufficient for understanding the tool's capabilities.

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 coverage is 100% with one parameter 'since' described as 'Time window (7d, 30d, 24h, all). Default: 7d'. The description only mentions 'for a time window' which adds no extra meaning beyond the schema. Baseline score of 3 is appropriate.

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 returns a granular model quality ledger with specific metrics (average score, sample count, findings/judge breakdown, escalation rate) per combination of model, effort, dimension, and sub-dimension. It gives an example, distinguishing it from sibling tools that focus on status, tasks, or spending.

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 quality metrics within a time window, but does not explicitly state when to use this tool over siblings like inspect_status, inspect_task, or inspect_swarm. No exclusions or alternative guidance is provided.

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