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

Annotations only declare readOnlyHint=false and destructiveHint=true; the description goes far beyond by disclosing the 15-minute lease, the takeover consequence, the PROGRESS_STALE / CLAIM_LOST / WRITE_LOCKED failure modes, that a refusal writes nothing, that only the claim is written, and that the token is a secret never returned. The one tension is destructiveHint=true against 'neither the task nor its history changes', but the loss-of-lease stake explains the conservative hint rather than contradicting it.

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?

Lifecycle and the progressPct caveat are front-loaded, and the response codes are packed efficiently. It is dense and slightly overlong — the plan SYNC-counter sentence is tangential to invoking the tool — but almost every clause carries operational value.

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 mutation tool with six parameters, no output schema, and heavy failure-mode surface, the description supplies both success and refusal response shapes, the full error-code vocabulary, and the side-effect boundary. Nothing an agent needs to call it safely appears missing.

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, but the description adds genuine meaning: progressPct is declared not measured and may decrease, 100 completes nothing, keepAlive bypasses the percentage within a 45-minute staleness window, and the token is a secret. It does not mention `expectedProjectId` at all, which keeps it off a 5.

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 first sentence gives a specific verb and resource (renew the claim lease) and binds it to the sibling that produces the token (`claim_task`) plus the sibling that actually completes work (`update_task({ status })`). An agent can distinguish it from claim_task, update_task, and archive_task without opening any schema.

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?

Explicit cadence rule (at least every 15 minutes or the task may be taken over), an explicit intended consequence, an explicit exception path (`keepAlive` for a watcher with its own 45-minute staleness limit), and explicit exclusions ('100 completes NOTHING — completion goes through update_task'). This is a full when/when-not/alternative statement.

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