feature_validate

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

With no annotations, the description carries the full burden and does well: it enumerates exactly which failure classes are caught (unknown template, unknown/missing/malformed refs, scalar-input failures) and explicitly discloses the limitation that unresolved geometry tags are only caught at feature_instantiate time. It does not state that the call is side-effect-free or how errors are surfaced, which keeps it from a 5.

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?

Front-loaded with the core action and the key differentiator ('WITHOUT building it'), followed by the failure inventory and the return shape. Informative density is high; the parenthetical aside about recipe_validate and the em-dash clause are slightly run-on but each earns its place.

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, and the description supplies the return contract {ok, problems}. It covers inputs, failure taxonomy, and the deferred-check boundary, so an agent has enough to invoke and interpret the result. Remaining gap is minor (no statement about idempotency/side effects), acceptable for a validation tool.

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, and it does: it names all three parameters (template, refs, inputs) and maps failure semantics to them — unknown template to 'template', unknown/missing/malformed reference to 'refs', scalar failures to 'inputs'. It doesn't specify the shape of refs/inputs objects, but the schema's additionalProperties leaves those open anyway.

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?

States a specific verb (validate) and resource (a feature instantiation {template, refs, inputs}) and immediately distinguishes itself from feature_instantiate with 'WITHOUT building it', plus names recipe_validate as the analogous sibling. An agent can pick this over feature_instantiate from the description alone.

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?

Gives clear context: this is the cheap pre-build check, and it is the front door before instantiation. It also names the boundary case (tag resolution is deferred to feature_instantiate time). It stops short of an explicit when-not/alternative instruction such as 'call feature_instantiate only after this passes'.

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