architect_sdd_materialize

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

Annotations declare a non-read-only, non-idempotent, non-destructive write, so the safety bar is lower, but the description adds no context beyond that: it does not say whether existing files are overwritten or merged, whether the run is resumable, what 'frozen basis_digest' means operationally, or what the caller gets back. 'Frozen' hints at immutability but is never explained, so the write semantics remain opaque.

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 front-loaded sentence with no filler, which is structurally sound, but it is essentially a dense noun phrase of undefined terms rather than a self-contained explanation. Brevity here reflects underspecification more than economy.

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?

This is a high-complexity tool: eight parameters, a nested object, two enums, no output schema, and non-idempotent write behavior. A single jargon sentence cannot convey what the agent needs to select and invoke it correctly, especially the profiles/presets and stub-only mode.

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 only 13% (just 'workspace'), leaving seven parameters undocumented, including two enums (preset, profile), a nested 'harvest' object, sources, reviewer, stub_only, and workspace_id. The description mentions none of them, so it fails to compensate for the coverage gap.

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 names a concrete verb ('Materialize') and lists artifacts produced (document tree, ledgers, wave micro-batches, basis_digest), which is more than a name restatement. However, the terminology is internal jargon and there is no differentiation from adjacent siblings like architect_sdd_init or architect_sdd_propose, so an agent cannot predict the boundary between this and those tools.

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 statement of when to call this tool, what prerequisites exist (e.g. whether architect_sdd_init must run first), or which alternative to prefer. The verb implies a scaffold-generation step, but that is inference, not guidance.

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