mason_init

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

With no annotations, the description carries the full burden and does well: it discloses that quickstart/map are read-only and deterministic, that setup mutates MCP config, instructions and lifecycle hooks while retaining original audit evidence, that evidence imports do not execute check commands, and that repeat calls refresh findings. It omits permission/auth requirements and error behavior, so not a 5.

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 the payoff ('Inspect this project now: returns ...'), then mode behavior and parameter context. Five dense sentences, each carrying information, though the mid-paragraph jump between setup semantics and optional-parameter notes makes it slightly harder to scan.

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 5-parameter, multi-mode tool with no output schema and no annotations, the description covers return contents, read-only vs mutating modes, and evidence import behavior. It does not spell out the absolute-path requirement for dir or the failure mode when setup is invoked without an unambiguous host, leaving modest gaps.

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 the schema already documents dir, base, host, mode, and evidence in detail; the description mostly restates host selects codex/claude, base picks the review comparison, and evidence imports CI manifests. It adds the useful nuance that findings refresh on repeat calls but contributes little parameter meaning beyond the schema.

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 concrete verb (inspect) and enumerates exactly what comes back: documentation audit findings, committed-diff review findings, decision/map status, and a quickstart playbook. It also distinguishes its three modes (quickstart/map/setup) so an agent can tell what the call produces. It does not explicitly position itself against siblings like full_analysis or mason_complete_init, which keeps it from a 5.

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?

Gives clear mode-level guidance: quickstart and map are read-only and deterministic, and setup should be used 'only when the user requests setup'. This is an explicit when/when-not rule. It stops short of naming sibling tools as alternatives, so it is not a 5.

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