Agent Memory Bridge

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

With no annotations provided, the description carries the full burden. It effectively discloses the fairness bias mechanism ('small fairness bias inside the oldest pending window') and lease reclamation logic ('another consumer can reclaim'). It lacks disclosure of failure modes, idempotency guarantees, or side effects on other polling consumers.

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?

Perfectly structured with two tight paragraphs. The first sentence captures the essential operation. The second paragraph efficiently covers usage timing, signal selection logic, and the fairness mechanism without redundancy. Every sentence advances understanding of the coordination pattern.

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?

Given the presence of an output schema (noted in context signals), the description appropriately focuses on the coordination semantics and claiming behavior rather than return values. With 100% parameter coverage in the schema and complex distributed-system behavior explained (leasing, fairness, filtering), the description is complete for this abstraction level.

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% (baseline 3). The description adds significant conceptual value beyond the schema by explaining the dynamic behavior when signal_id is omitted (next eligible signal selection), the fairness bias affecting filtering, and the coordination pattern (claim before act), which helps agents understand the intent behind tags_any and correlation_id.

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 opens with a specific verb ('Claim') and resource ('one signal'), specifies the mechanism ('short lease'), and states the domain ('lightweight work coordination'). It clearly distinguishes this from sibling tools by emphasizing the lease-based claiming pattern versus acknowledgment (ack_signal) or lease extension (extend_signal_lease).

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?

Provides explicit usage context: 'Use this when a worker should take ownership of a pending signal before it acts.' It also explains the polling behavior and fairness bias for when signal_id is omitted. However, it lacks explicit guidance on when NOT to use it or direct references to siblings like ack_signal or extend_signal_lease for the complete lifecycle.

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