ow_status

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

The description discloses network access behavior and caching semantics, which complements the readOnly and idempotent annotations. It does not mention errors or rate limits, but the annotations already convey the safety profile.

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 two sentences, concise, and free of unnecessary detail. It packs purpose, usage, and behavioral notes efficiently.

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 status tool with one optional parameter, the description is complete enough to understand what it does and how to use it. It does not describe output format, but the output schema is already provided.

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 single refresh parameter is semantically explained by the description: setting it triggers bounded cached probes, while the default avoids network access. This provides enough context despite the schema lacking a parameter description.

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 observed source health, capabilities, and stored coverage, giving a specific verb and resource. It does not explicitly differentiate from sibling tools, but the focus on 'observed' and 'stored' implies read-only status reporting.

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 when to use the refresh parameter versus the default behavior: refresh performs bounded cached probes, while default performs no network access. This gives practical usage guidance, though it does not mention alternative sibling tools.

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