interactive_adr_planning

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

With readOnlyHint=false, the annotations are neutral and carry little safety information, so the description bears the burden. It does add behavioral context beyond the annotations: the multi-phase guided workflow, research integration, option evaluation, and automatic ADR generation. However, it does not disclose side effects such as whether TODOs or ADR files are written to disk, or whether sessions persist state — meaningful gaps for a tool with generateTodos and generate_adr operations.

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?

Two sentences with no filler. The primary purpose is front-loaded in the first sentence, and the second sentence delivers an actionable prerequisite tip rather than decoration. It earns its length; only a slightly dense comma-separated feature list keeps it from a 5.

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 tool with 13 operations, 6 parameters, and no output schema, the description gives a solid high-level orientation but leaves the session orchestration implicit — the agent must infer the start/continue/provide_input/.../complete lifecycle from the operation enum alone. The TIP about reading project context partially compensates by pointing the agent to external grounding, but return behavior and the phase-by-phase contract are unexplained.

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 baseline is 3; the schema already documents input, operation, sessionId, projectPath, autoResearch, and generateTodos. The description adds no parameter-specific meaning beyond loosely mirroring the workflow (research integration maps to autoResearch/request_research, ADR generation maps to generate_adr). It neither compensates for gaps nor contradicts 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?

The description states a specific verb+resource: it is an 'Interactive guided ADR planning and creation tool' that 'walks users through structured decision-making process.' The 'interactive guided' framing implicitly differentiates it from batch/one-shot siblings like generate_adrs_from_prd and suggest_adrs, though it never names them explicitly, so the differentiation is implicit rather than explicit.

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?

The only usage guidance is the TIP to read @.mcp-server-context.md before starting, which is a useful prerequisite but does not address tool selection. There is no statement of when to use this tool versus the many ADR-related siblings (generate_adrs_from_prd, suggest_adrs, generate_adr_from_decision), no exclusions, and no conditions. The agent must infer usage context from the name and operation enum.

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