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

Annotations already declare readOnlyHint=true, so the safety profile is covered. Beyond that the description discloses what each kind actually returns (operators for filter fields, custom field numeric ids for output columns) and even names the underlying REST paths, adding useful behavioral context without needing to discuss caching or pagination for a metadata lookup.

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?

Two front-loaded sentences with no filler: the purpose and the kind split come first, the mandatory ordering call comes last. Every clause carries an actionable 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?

There is no output schema, so the description compensates by summarizing the return payload for each kind. Combined with full schema coverage and annotations, an agent has everything needed to call this prerequisite tool correctly.

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 100% with both params enum-constrained, so the baseline is 3. The description goes further by explaining the semantic difference between the two enum values and what each returns, which meaningfully supplements the terse schema descriptions ('Filter fields or output columns').

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 ('Discover') plus resource ('the field names neon_search accepts') and disambiguates the two modes by explaining what kind=searchFields yields (filterable fields with allowed operators) versus kind=outputFields (returnable columns, standard plus custom numeric ids). An agent can distinguish this from the many neon_get_*/neon_list_* siblings without opening any schema.

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 explicitly states the ordering constraint 'Call this before neon_search', naming the sibling tool that consumes the result. This is a clear when-to-use rule that routes the agent correctly rather than leaving sequencing to inference.

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