cassette_config

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

Without annotations, the description must carry the full transparency burden. It discloses that changes are 'persisted for the session' and 'applied from the next cassette_run_job turn,' and warns of default matching. However, it does not mention potential side effects or whether changes are reversible, which is a gap for a mutation tool.

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 concise at three sentences, front-loaded with the core purpose, and each sentence adds unique value: purpose, usage pattern, and default behavior warning. No wasted words.

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?

Given the presence of an output schema, the description appropriately focuses on behavior rather than return values. It covers what to expect when reading ('current choice and available options') and when writing (persistence and timing). Minor gap: does not explicitly state that writing returns the updated config, but the output schema likely covers this.

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?

With 0% schema description coverage, the description effectively compensates by explaining the purpose and usage of each parameter: 'model (id or label)' and 'thinking_level' with implied enum set. It clarifies the read/write pattern using session_id alone vs. with parameters, adding meaning beyond the bare 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 clearly states the tool's function: 'Get or set the session's Cassette model and thinking level.' It uses specific verbs (Get, set) and resources (model, thinking level), and distinguishes itself from sibling tools like cassette_run_job by focusing on configuration rather than execution.

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 explicit guidance: call with only session_id to read current config, or pass model/thinking_level to modify. It also advises 'change only when the user asks,' indicating appropriate invocation context. However, it does not explicitly state when not to use this tool versus alternatives, though the context implies it.

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