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

Annotations already declare this writes (readOnlyHint=false), is idempotent and non-destructive; the description adds genuinely new behavior: it stores the NAME of the transcript, never its contents (a privacy/data-scope guarantee), and that model/subagent status is recorded only when the harness reports it. It does not cover error behavior (e.g., what happens with a non-session key), which keeps this short of a 5.

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 core action is in the first clause, caller/skip guidance follows, and the storage-scope caveat is compressed into one short sentence. Three dense sentences with no restated title or filler.

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 6-parameter write tool with no output schema, it covers action, caller, precondition, what is and is not persisted, and the optionality of secondary fields — enough for an agent to call it correctly without further context.

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 100%, so the baseline is 3; the description still adds useful semantics by framing model and agentType as conditional facts the harness may never supply ('when the harness reports them'), discouraging an agent from fabricating them. It does not add format or syntax detail for transcriptId or harness beyond what the schema already states.

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 precise verb and resource ('Record this harness session's transcript id on YOUR session key') and immediately names the consumer benefit (Dash conversation view, `claude --resume <id>`). It is clearly distinguishable from nearby siblings like mint_session_key or heartbeat, since those mint or ping a key while this attaches a transcript id to an existing one.

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?

Explicitly says who calls it and when: the watchdog proxy does it automatically via SessionStart/GROK_SESSION_ID, and 'an agent only needs it when running without the proxy.' It also states the hard prerequisite 'Session keys only,' giving an agent both the trigger and the precondition for use.

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