typescript_diagnostics

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

The description discloses key behavioral traits: it persists ProjectFinding rows (a side effect), runs a broad typecheck, and returns bounded findings. Annotations already indicate not read-only and not idempotent, but the description adds context about persistence and typecheck scope. However, it doesn't detail whether the operation is destructive or any rate limiting.

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 extremely concise: two sentences with no filler. It front-loads the core purpose ('Explicit Reef ingestion tool for semantic TypeScript compiler diagnostics') and efficiently adds usage guidance. Every sentence adds value.

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 complexity (5 parameters, side effects, output schema present), the description covers the primary behavior and distinguishes from a sibling. The output schema likely handles return values, so not describing them is acceptable. However, it could briefly mention the effect on the working tree or that it may be slow due to broad typecheck.

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 description coverage is 0%, so the description must compensate by explaining each parameter. It only implies tsconfigPath and maxFindings but completely omits projectId, projectRef, and files. These are not self-explanatory from names alone, leaving the agent without critical details about what values are expected.

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 identifies the tool as a 'semantic TypeScript compiler diagnostics' tool, specifying exactly what it does: read tsconfig, run TypeScript with no emit, persist findings, and return bounded results. It explicitly distinguishes from the sibling tool diagnostic_refresh for syntax-only refresh, making its purpose unambiguous.

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 provides explicit guidance on when to use this tool versus alternatives: 'This may run a broad typecheck; use diagnostic_refresh with typescript_syntax for syntax-only refresh.' It tells the agent exactly which sibling tool to use for a lighter operation, making usage decisions clear.

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