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

The description discloses that the tool calls an external AI provider, consumes tokens/may cost money, stores the result, and requires specific admin and key configuration. These details go beyond the annotations (which only indicate mutation and non-idempotency) and provide essential operational context for a side-effecting 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?

Three sentences are used: the core action/outputs, the side effects (provider call, cost, storage), and the prerequisites. The description is front-loaded with the action and contains no filler; every clause contributes useful information.

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 complex, side-effecting tool, the description covers the action, analysis inputs, output types, cost, storage, and admin requirements. An output schema exists so return-value details need not be explained, and the description is sufficient to guide an agent even among many sibling tools.

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 schema already describes model and provider overrides, and the tool description mentions analyzing 'an annotation,' which loosely maps to annotation_id. However, annotation_id lacks a schema description, and the description does not clarify the override parameters or the required annotation reference beyond the schema. Coverage is 67%, so the description adds modest semantic value.

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 ('Run the AI Diagnosis Engine') and names the resource (an annotation). It enumerates concrete outputs (ranked root causes, confidence score, suggested fix, source files) and distinguishes itself from the sibling get_annotation_analysis by emphasizing that it runs and stores a new diagnosis rather than retrieving existing analysis.

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 gives clear usage context: this tool generates a new AI diagnosis, with prerequisites (admin-enabled AI + diagnosis, key set) and cost implications. It does not explicitly name get_annotation_analysis as the read-only alternative, but the operational context is unambiguous enough for an agent to decide.

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