Recommend architecture rules

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the trailing 'Read-only.' is redundant rather than contradictory. The description's real contribution is describing what the recommendation contains (enforce-now, reportOnly, review-before-enforcing, peer-adopted gaps), which is meaningful behavioral context given there is no output schema.

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 dense sentence with the core action and the read-only guarantee front-loaded, and no filler. It is long, but every clause maps to a distinct category of output, so 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?

With no output schema, the description usefully covers the return shape, and the one parameter is fully documented. The only real gap is the unstated relationship to archprint_scan as a prerequisite for the 'evidence' it consumes.

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 100% for the single path parameter, and the schema itself clarifies it is a local directory defaulting to '.', not a URL. The description adds nothing about path beyond that, so the baseline 3 is appropriate.

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 (recommend) and resource (an architecture rule set) and pins the scope to this repo's evidence and detected stack, then enumerates the four categories of recommendation. It is unambiguous about what the tool produces, though it never names the sibling tools to draw a boundary against archprint_scan or archprint_explain.

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?

Usage is implied by the enumeration (use it when you want to know what to enforce, what is reportOnly, what to review, what peers adopt), but there is no explicit when-to-use statement, no exclusion, and no stated prerequisite such as whether archprint_scan must run first to produce the evidence this tool consumes.

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