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

Annotations only state readOnlyHint=false and non-idempotent; the description adds the meaningful behavior — the call advances session state, returns the next question with progress, and may carry milestone/insight payloads that must be surfaced in a specific format. It does not cover failure modes (invalid question_id, stale session_id) or what happens after remaining=0 beyond handing off to finish.

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 action, then sequencing rules and formatting guidance. Every sentence carries an instruction (milestone line, insight block, finish handoff, clarification rule), though the presentation-format detail is slightly verbose for a description whose job is routing.

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?

There is no output schema, so the description correctly compensates by explaining what comes back (next question, progress, milestone, insight) and how to render it. It is nearly complete for a conversational step tool, with only error/stale-session behavior and session_id semantics left 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 coverage is 50% and session_id is undocumented in both places, but the description adds real meaning the schema lacks: answers carries the letter exactly as the user said it, one letter per current question, and no substitution by the agent. That is more than the nested schema's own field descriptions provide.

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 two-part verb+resource: record the user's answer to the current question (A/B/C/D) and retrieve the NEXT question with progress. This is clearly distinguishable from ruforge_diagnostic_finish, ruforge_diagnostic_questions and ruforge_diagnostic_start without opening the schema.

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?

Explicit routing: call ruforge_diagnostic_finish when remaining=0; if the user replies with free text instead of a letter, ask for the letter rather than interpreting it. It also states the agent must not choose an option on the user's behalf, which is a real anti-pattern guard.

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