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

The description adds behavioral context beyond the readOnlyHint annotation: it returns null if no diagnosis has been generated, and it retrieves only the 'latest' stored diagnosis. This is useful non-obvious behavior not captured in the annotations.

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 only two sentences, with the action front-loaded and every word earning its place. The second sentence adds essential behavioral detail and the alternative tool, making it highly efficient.

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 an output schema exists, return value details are not needed. The description covers the tool's core purpose, null behavior, and creation alternative, which is sufficient for a simple one-parameter read operation with strong annotations.

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 0%, so the description must compensate. It implies annotation_id via 'for an annotation' but does not explicitly name the parameter or provide additional semantic context (e.g., format, source of the ID). The meaning is inferable from the tool's name and context.

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 uses a specific verb 'Read' and a clear resource 'latest stored AI diagnosis for an annotation', listing contents (root causes, confidence, suggested fix, source files). This distinguishes it from sibling tools like get_annotation and diagnose_annotation.

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?

It explicitly says 'run diagnose_annotation to create one' when none exists, providing a clear alternative for a specific situation. The null return condition also signals when to use this tool vs. the alternative.

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