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

The description adds substantial behavioral context beyond the annotations: it describes the return format (ordered diagnostic checks, likely causes, fixes, documentation links), how unknown symptom keys are handled, and the exact matching rule for the description parameter. Annotations already declare read-only and idempotent, but the description adds rich operational detail about what the agent will get back and how matching works.

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 front-loaded with the purpose and then efficiently lists coverage, return format, limitations, and matching behavior. Every sentence contributes, though the long symptom list is somewhat dense. It is appropriately sized but could be slightly tighter.

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 presence of an output schema and detailed annotations, the description is complete: it explains the tool's purpose, supported symptoms, input flexibility, return content, and matching behavior. Nothing critical for correct invocation is missing.

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%, so the baseline is 3. The description adds meaning beyond the schema by explaining that a symptom or description is accepted without requiring an ID, and by specifying the matching behavior for description (verbatim match only, otherwise symptom list returned). Some of this overlaps with schema descriptions, but the matching logic is additional 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 states a specific verb 'Diagnose' and resource 'referral tracking and program problems', and explicitly distinguishes itself from read tools by saying 'It does not read program or participant records.' This differentiates it from siblings like growsurf_get_participant or growsurf_get_campaign without needing to name them.

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 provides clear context: accepts a symptom or description without requiring program or participant IDs, and lists the problem types it covers. It also includes an exclusion ('does not read program or participant records'), but it does not explicitly name alternative tools for reading records. This is clear contextual guidance but falls short of explicit when-to-use/when-not/alternatives.

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