manage_recovery_strategy

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

Annotations already cover read-only and destructive hints, so the bar for disclosure is lower. The description adds useful behavioral detail beyond that: start_date defaults to today, category is inferred from the name, strategy_name is a case-insensitive substring, and ambiguous matches produce an error with candidate IDs to retry with.

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?

The description is organized into clear sections: trigger cases, selector rules, and post-add follow-up. It stays front-loaded and every block earns its place, though the post-add paragraph is fairly verbose and could be trimmed without losing the required conversational loop.

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 12-parameter mutation tool with one required field in schema, this description covers the most likely failure points: how to resolve strategy names, what to infer, what defaults to use, how to handle errors, and what to do after a successful add. The output schema exists, so the description does not need to explain return values.

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?

Even though the schema has 100% parameter coverage, the description adds critical semantics the schema does not express: exactly one of id or strategy_name is required for update/end/delete, name is the only truly required field for add, and optional fields like duration_minutes and time_of_day should be confirmed after an add. This is highly actionable guidance 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?

The opening line uses a specific verb-resource pairing: 'Add, update, end, or delete a recovery/mindfulness strategy,' and covers the full set of actions. This distinguishes the tool from session-level siblings like log_recovery_session and list_recovery_strategies by making it clear this tool manages the strategy lifecycle.

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 description provides concrete trigger cases: when the user describes a new practice, changes a schedule, stops a practice, or removes one. It also says to ASK only if the name is missing, but it does not explicitly name alternative siblings or state negative 'do not use this when' guidance.

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