pick_fields

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

No annotations are provided, so the description carries the full burden, and it does disclose the return shape ('the projected array containing only the specified fields'), which tells the agent the input array is not mutated. It omits edge behavior — unknown field names, non-array paths, and whether nested field names are supported — so it is good but not complete.

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 one-line purpose is front-loaded, then the analogy, then per-parameter detail. The Args/Returns scaffolding is a little formal for a three-parameter tool but every line carries information.

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?

With an output schema present, the Returns section is somewhat redundant, and its presence doesn't compensate for what is missing: no annotations, no statement of preconditions (document must be loaded), and no error semantics for missing fields or non-array paths. Adequate for a simple projection but leaves real gaps for an agent operating blind on behavior.

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 Args block is doing real work: it explains alias refers to a loaded document, path is dot-notation to an array of objects, and fields is a list with a concrete example. Each parameter gains meaning beyond its bare type, though dot-notation syntax and alias resolution are only sketched, not specified.

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 and resource — 'Extract specific fields from each object in an array' — and reinforces it with the SQL SELECT projection analogy. It is clearly distinct from filtering siblings like filter_objects, though it never names an alternative explicitly.

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?

Usage is implied by the projection analogy rather than stated: an agent can infer this is for narrowing columns, not filtering rows. There is no explicit when/when-not, no mention that a document must be loaded via load_json first, and no guidance on combining with filter_objects or jsonpath_query.

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