record_handoff

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

Annotations already declare readOnlyHint=false (write) and destructiveHint=true, so the description's 'Write' phrasing is consistent and adds the destination target (chain link and data directory). However, it does not explain what the destructiveHint means here — whether existing handoff data is overwritten, what a chain link write implies, or the idempotency behavior that idempotentHint=true promises. With annotations carrying the safety profile, a 3 is appropriate.

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 short sentences, front-loaded with the action and target before the payload enumeration. No filler or redundancy; only minor room to tighten phrasing.

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?

An output schema and annotations are present, so return values and safety hints need not be restated. Still, for a destructive write into a chain-of-handoffs workflow, the description omits what happens to existing handoff data and how it relates to the surrounding chain tools, leaving a moderate gap.

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?

Reported top-level schema coverage is 0% because the single 'params' wrapper is undocumented, but the nested RecordHandoffInput properties carry rich descriptions in the schema. The description's list of captured content loosely maps to those nested fields (decisions, files changed, open threads, next-session recommendation) without adding format or cardinality details beyond the schema, so baseline 3 is correct.

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 names a specific verb (Write), resource (session-end handoff) and destination (chain link and data directory), then enumerates the captured payload (decisions, files changed, open threads, emotional context, next-session recommendation). This is clear enough to distinguish it from generic record_* siblings, though it never names an alternative tool explicitly.

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 phrase 'session-end handoff' implies the timing (end of session), which gives some usage signal, but there is no explicit when-to-use guidance, no prerequisites, and no reference to a related sibling such as add_chain_link or complete_chain_link. Usage is inferred rather than stated.

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