discover_table

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

Despite annotations indicating readOnlyHint and openWorldHint, the description adds crucial behavioral context: it registers new tools (side effect), caches schemas for 30 minutes, and states what tools become available. This is transparent about the tool's side effects and temporal behavior.

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 compact, with only three sentences. It front-loads the core purpose, lists the generated tools for clarity, and mentions the cache duration without unnecessary detail.

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 tool's complexity and side effects, the description is well-rounded: it covers what the tool does, the resulting tools, the operations filter, and the caching behavior. It doesn't need to explain return values because there is no output schema, but the description sufficiently explains the tool's effect.

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 input schema already has 100% coverage with descriptions for both 'table' and 'operations'. The description adds purpose by explaining that 'operations' controls which dynamic tools are enabled and that the default is all. The schema alone doesn't convey the side effect of tool registration, so the description adds 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 clearly states the tool's purpose: discovering a ServiceNow table schema and registering dynamic CRUD tools for it. It also distinguishes itself by listing the exact tools that become available and mentioning the 30-minute cache.

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 implies when to use this tool by noting that it registers dynamic tools, but it doesn't explicitly contrast with alternatives like get_table_schema or query_records. It lacks an explicit 'use this instead of X' statement, but the context of creating new dynamic tools is clear.

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