template_fields

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses concrete behavior: returning field ids, prompts, required/repeatable flags, constraints like regex/prefix/datatype, and allowed values; plus source semantics for 'live' vs 'bundled-snapshot' and 'driftedFromSnapshot.' It also clarifies that templates may be stale when the network is unavailable.

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 dense but every sentence earns its place: purpose, timing, return contents, step values, and source-freshness semantics are all relevant. The most important scoping information is front-loaded before implementation details.

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?

For a two-parameter lookup tool with no output schema and no annotations, the description is remarkably complete. It tells an agent what the tool returns, which parameter values are valid, what the freshness/drift states mean, and when to call it. The only small gap is explicit treatment of the `live` parameter, but it is not enough to undermine completeness.

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. It does this very well for `step` by documenting accepted aliases and listing all known step values, but it does not directly explain the `live` boolean parameter beyond the broader 'live' vs 'bundled-snapshot' distinction in the source discussion.

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 opens with a precise definition: 'The exact form fields of one FORRT chain step, from the live template.' It names the resource, scope, and what the tool returns, and the contrast with validation/verification siblings ('Call this BEFORE drafting any nanopub field') makes its role 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?

It gives explicit timing context: 'Call this BEFORE drafting any nanopub field,' and explains why the template itself is the schema. It also enumerates known step aliases and values. However, it does not explicitly name alternative tools or state when not to use this tool.

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