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

Goes well beyond annotations (idempotentHint=true, readOnlyHint=false) by disclosing the renewal semantics, the deliberate abandonment design, and the rationale that silence is the only signal the board has. It also explains that blocked/needs_input statuses 'park the task for the human,' which is behavioral context the annotations cannot express. 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?

Four sentences, roughly 100 words, with the core instruction front-loaded ('Say you are still working') before the mechanics and rationale. Every sentence earns its place — even the dead-agent rationale is justified behavioral transparency rather than fluff. No redundancy with the schema.

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 5-parameter tool with no output schema, the description covers the operational essentials: cadence, failure mode, and the two use cases. The only notable gap is that it does not hint at what the call returns (e.g., renewed expiry time), which matters given no output schema exists. The learnings parameter's nuanced rules are fully handled by the schema, so their absence from the description is acceptable.

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 schema already documents all five parameters, including the status enum semantics and the rich learnings guidance. The description adds the cadence context linking runId/leaseToken to the renew cycle, but that is marginal on top of the schema already saying 'returned by start_task.' Baseline 3 is appropriate.

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 states a clear, specific purpose in the first sentence — 'Say you are still working' — and unpacks it as a claim-renewal heartbeat tied to renewEverySeconds from start_task. It distinguishes itself from siblings by explaining that without this call the task is 'treated as abandoned and offered to someone else,' which no other sibling covers. The secondary purpose ('the place to say you are blocked or waiting on the user') is also explicit.

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?

Gives explicit when-to-use guidance: 'call this at least every renewEverySeconds returned by start_task, and it renews,' plus the consequence of silence (abandonment). It also names the secondary trigger ('blocked or waiting on the user'). It stops short of a 5 because it never explicitly names sibling alternatives or says when NOT to use it (e.g., use complete_task when done), leaving that to inference.

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