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

Annotations already declare the safety profile (readOnly=false, idempotent=true, destructive=false), so the bar is lower. The description still adds real context beyond them: it discloses that the operation is delegated to a local agent and that the server persists only bounded metadata plus an attested outcome, which explains why details is field-restricted.

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 the action first and the storage caveat second; every clause carries information. The compressed storage clause is slightly dense but not wasteful.

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 required-param mutation with a nested object, an idempotency key, optimistic-concurrency versioning, and no output schema, the description covers the delegation model but omits what a successful finish changes, what happens if no local agent is connected, and how version conflicts surface.

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 100%, so the schema itself documents nodeId, projectId, idempotencyKey, expectedVersion and the details object. The description's 'bounded metadata' phrase loosely reinforces the details constraint but adds no semantics beyond the schema, so baseline 3 applies.

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 concrete verb+resource (finish node work) and names the actor it targets (the connected local agent). It is distinguishable from siblings like start_node_work and finish_agent_session by the 'node work' scope, though it never names an alternative explicitly.

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?

Usage is only implied by the name pairing with start_node_work; there is no statement of when to call this versus finish_agent_session, finalize_agent_execution, or an abort path, and no precondition such as an active execution or connected agent being required.

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