architect_sdd_prepare_check

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false; the description usefully adds that it mutates artifacts by stripping thinking blocks, tightening lines, repairing frontmatter and freezing a digest, which tells the agent files are rewritten in place. It does not disclose that the frozen digest may be invalidated by reruns (consistent with idempotentHint=false) nor whether partial failures leave artifacts in an inconsistent state.

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?

A single front-loaded sentence with the action verb first and a compact parenthetical enumeration; every clause carries information. Slightly dense, but nothing is wasted.

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 mutating multi-step pipeline with no output schema and incomplete parameter coverage, yet the description says nothing about return values, whether it reports per-step results, error behavior, or ordering relative to sibling stages — despite the tool name also implying a 'check' phase the description never mentions.

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 coverage is only 20% (only `workspace` is described), so the description must compensate. It partially does: the named steps map plausibly onto `tighten`, `style_fix` and `stamp`, but `pad_to_min` is never explained, and it is unclear whether 'strip thinking', 'repair frontmatter' and 'freeze digest' are unconditional or controlled by any flag.

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 ('Run') and resource ('built-in post-processing pipeline') and enumerates the six concrete steps it performs, so an agent knows exactly what work happens. It does not differentiate itself from plausible siblings such as architect_style_check, architect_language_repair or architect_sdd_check, which overlap with the 'style fix' and 'repair frontmatter' steps.

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?

No guidance on when to call this versus the many sibling check/repair tools, no stated preconditions (e.g. that a prior extract/materialize stage produced the artifacts), and no mention of what to do if the pipeline fails. The agent must infer sequencing entirely.

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