compile_spec

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

With no annotations, the description carries the full behavioral burden and says nothing about side effects — whether a compile writes or overwrites a draft, is idempotent, or requires prior claims/unknowns to exist. Only the existence of an output schema saves the agent from total blindness about results.

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?

One short sentence, front-loaded with the verb and the output artifact. No filler. The brevity is only a problem because nothing else compensates, not because the sentence is padded.

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 tool with zero annotation coverage and no parameter documentation, the description should explain the lifecycle position and side effects. The output schema covers return values, but nothing tells the agent what must exist beforehand or what this changes.

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% for the single 'feature' parameter. The phrase 'for a feature' weakly signals that the argument is a feature identifier, but gives no format, expected naming, or whether it must match an existing feature record.

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 verb 'compile' and resource 'spec draft' are named, and the parenthetical 'model + claims + unknowns' hints at what gets produced. But 'compile' is jargon — it's unclear whether this assembles, validates, or generates — and there's no explicit contrast with siblings like review_spec or release_spec that sit in the same lifecycle.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. An agent can infer from sibling names that a propose → compile → review → release pipeline may exist, but the description itself offers nothing to route on.

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