Finalize Session

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

The description goes beyond annotations by disclosing the identity forgery check, requiring the caller to match the peer host's token/clientInfo, and stating that the 'converged' outcome is only sealed by the runtime. It also notes the max characters for reason and that 'max-rounds' is only written by runtime/sweep. These are significant behavioral traits not present in the annotations (which only provide idempotentHint/destructiveHint). There is no contradiction with annotations.

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 dense but appropriately sized for the complexity, covering the core purpose first, then auth requirements, then runtime constraints. The sentences are structured logically, front-loading the primary action. It could be slightly more concise by cutting the last clause about 'max-rounds-sweep', which is tangential, but it's acceptable.

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 tool's complexity (auth checks, runtime-only outcomes, limited outcomes), the description covers the essential use case and constraints. It lacks explicit mention of return values (no output schema, so description could mention what is returned, e.g., confirmation or error details), and it doesn't explain what happens if the session is already terminal. However, most critical decision-making info is present.

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 0%, so the description must explain parameters, and it does partially. It explains 'reason' (optional, max 200 chars) and 'caller' (must be host's own identity, forgery check), but does not explain 'session_id' format (though schema has pattern) or 'response_format' (schema has default). It doesn't add much beyond the schema for session_id, but for caller it adds crucial semantics. With 0% coverage, description should carry more, but it covers the most important behavioral parameter.

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 that the tool closes a non-terminal durable session as 'aborted' with an optional reason, which is a specific action on a specific resource. It does not explicitly differentiate from siblings, but the outcome enum (only 'aborted') and the mention of 'non-terminal' make its purpose distinct, though not explicitly naming alternatives.

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 some context on when to use it: it's for aborted sessions, and it explains that 'converged' is only sealed by the runtime, not by this tool. However, it doesn't explicitly say 'use this instead of session_cancel_job' or similar, and doesn't mention when-not-to-use it (e.g., if the session is already terminal). The guidance is implied through the outcome constraint but not explicit.

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