heartbeat

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

No annotations are provided, so the description carries full behavioral burden. It conveys that lease state is mutated, but says nothing about permissions/auth, what happens if the lease already expired, whether the operation is idempotent, or what the response contains.

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?

A single front-loaded sentence with no filler, stating the action immediately. It is efficient, though arguably too terse for a 4-parameter tool with zero schema documentation.

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 tool with 4 parameters, no output schema, and no annotations, the description is thin: it omits auth requirements, lease semantics (default 900s), required parameters, and failure modes. An agent would be guessing at much of the invocation contract.

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 0% across 4 parameters, so the description must compensate. It implicitly maps to subtask_id and lease_seconds (the lease being extended), but leaves 'agent' and 'api_key' unexplained and adds no format or constraint detail beyond the schema.

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 specific verb and resource ('Extend the lease on a subtask'), so the agent knows this is a lease-renewal operation rather than a task state transition. It does not explicitly contrast itself with siblings like claim_subtask, pickup, or start_work, so it falls short of a 5.

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?

'on a subtask you are working on' implies the usage context (call it while actively working to keep the lease alive), but gives no explicit when-to-use, when-not, cadence, or alternatives. 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.