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

Annotations declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds meaningful context beyond annotations: it clarifies that the server stores only bounded metadata and an attested outcome, which helps the agent understand the persistence and side-effect profile. It does not contradict 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?

The description is a single sentence that is reasonably concise and front-loads the primary action. However, it packs two distinct ideas (requesting work and server storage behavior) into one sentence, which slightly reduces clarity. It earns its place but could be split for better readability.

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 tool has 6 parameters, a nested object, no output schema, and no parameter documentation in the schema, the description is insufficient. It does not explain the relationship between the parameters, what constitutes a valid 'details' object, or what the agent should expect in return. The description covers the high-level behavior but leaves critical invocation details unaddressed.

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 description coverage is 0%, so the description carries the full burden for parameter semantics. The description mentions 'bounded metadata' but does not explain the meaning or purpose of key parameters like projectId, nodeId, idempotencyKey, details, sessionId, or executionId. The nested 'details' object is entirely unexplained, leaving the agent without guidance on how to populate it.

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 specific verb ('Request the connected local agent to start node work') and identifies the resource ('node work'), which clearly distinguishes it from siblings like finish_node_work and submit_node_instruction. However, it doesn't explicitly name the sibling it is not, and 'node work' is somewhat domain-specific without further elaboration.

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?

The description implies usage context ('connected local agent', 'server stores only bounded metadata') but does not explicitly state when to use this tool versus alternatives like submit_node_instruction or finish_node_work. No exclusions or alternative routing is provided, leaving the agent to infer the appropriate context.

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