Render a spec-loop feature

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

Beyond annotations (readOnlyHint=false, idempotent=true, destructive=false), the description discloses real side effects: it writes into rendered/ and additionally refreshes the manifest and spec/README.md. It also flags a hard refusal guard. It stops short of describing what the refusal error looks like or how to clear it.

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 sentences, zero filler, with the primary action and its outputs front-loaded before the refusal caveat. Every clause 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?

An output schema exists, so return values need not be explained, and side effects are covered. The main gap is the unverified-owner-edits state: the description states a blocking condition without pointing at the sibling (reconcile/validate) that resolves it, leaving the agent stuck on refusal.

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%, so both parameters are already documented in the schema. The description adds only an implied notion that `feature` targets a feature.json, and says nothing about the `root` resolution chain, so baseline 3 is correct.

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?

Names a specific verb (project/render) and resource (a spec-loop feature.json into rendered/), and enumerates the collateral outputs (manifest, spec/README.md). It does not explicitly contrast itself with siblings like validate, diff, or reconcile, so an agent must infer the boundary.

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?

The clause 'Refuses while owner edits are unverified' is a precondition that implies when not to call, which is useful. However, there is no explicit statement of when to choose render over diff/validate/reconcile, nor which tool resolves the unverified state.

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