Arch Advisor

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

No annotations are supplied, so the description carries the full behavioral burden and does not meet it. It never says whether actions like generate_c4 write files to disk, whether the tool is read-only, what permissions or project state it requires, or how expensive a full analysis is. Only the A-F grade output is disclosed, leaving the mutation/side-effect profile of a seven-parameter tool entirely unstated.

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?

Front-loaded with a one-sentence capability summary followed by a scannable action list; nothing is padded. The sole redundancy is restating 'Architectural Advisor - analyze architecture' in the header.

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 seven-parameter, multi-mode tool with no annotations and no output schema, the definition leaves too much open: parameter usage, whether any action has side effects, and the shape of results beyond 'score (A-F grade)'. An agent could pick an action but not confidently configure or interpret the call.

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 29%, with only project_path and limit documented in the schema, yet the description explains no parameters at all. enabled_rules, disabled_rules, and severity_filter are undocumented in both places, and c4_level's relationship to the generate_c4 action is only inferable from the action name. With low coverage, the description was required to compensate and does not.

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 opening line names a specific verb set and resources: analyze architecture, detect antipatterns, generate C4 diagrams, suggest refactoring. The action enumeration makes the tool's scope unambiguous even against a large sibling list. It stops short of explicitly distinguishing itself from neighbors like mcp_m7_scope or mcp_m7_get_patterns, which also touch architectural concerns.

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?

Each action is paired with a one-line intent (analyze = full analysis with grade, score = quick summary, critical_issues = only critical problems), which gives the agent concrete context for picking a mode. There are no exclusion rules or guidance on when another sibling tool would be preferable, so it lands at clear-context-without-exclusions.

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