describe

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

With no annotations provided, the description carries full burden. It discloses behavioral traits: the deny-list of high-noise keys in verbose mode, the requirement of table for list_script_fields, and the flow differences for the action parameter. No contradictions.

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 fairly long but structured logically: first sentence states the dual purpose, then parameter details. It is front-loaded. Could be slightly more concise, but 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 5 parameters, no required ones, and presence of output schema, the description provides sufficient context for using the tool. It explains return structure indirectly but adequately. Slight gap: does not explicitly mention pagination or limits, but for metadata retrieval it may be complete.

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%, but the description adds extensive meaning to each parameter beyond type/defaults. It explains what 'fields', 'verbose', 'include_docs', and 'action' do, including nuanced behaviors (e.g., empty fields = all fields).

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 returns slim field metadata for a table, with an alternative mode to list script-bearing fields. It uses specific verbs ('Return', 'list') and distinguishes itself from sibling tools like query or record_read by focusing on metadata rather than data.

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 explains parameter usage in detail, including the requirement for 'table' even with 'action', and the effect of each parameter. While it does not explicitly state when not to use the tool or list direct alternatives, the context from sibling tools implies appropriate use cases.

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