gateway_work_complete

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

Annotations contain only a title, so the description must carry the behavioral disclosure burden. It does disclose the core behavioral contract: this tool records verification evidence and gates downstream acceptance. It could go further by explaining what happens when success=false or what side effects the evidence recording produces, but the main consequence is clearly stated.

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 compact and front-loaded: first the purpose, then the one non-obvious parameter format, then the sequencing constraint. Every sentence contributes actionable guidance and nothing is wasted.

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?

The description covers the tool's role in the workflow and provides critical parameter guidance for result_refs_json. With no annotations and several required parameters still unexplained, however, an agent may not know valid values for evidence_state or how metrics_json/admin_actions affect behavior. The output schema helps with outputs, but input semantics remain partially under-specified.

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 must compensate for undocumented parameters. It usefully explains result_refs_json's expected JSON-array shape with type/uri/title and examples, but it leaves the other required parameters — evidence_state, work_id, success — and optional metrics_json/admin_actions semantically unexplained. This is only partial compensation for the schema gap.

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 action — 'Finish execution and record evidence' — on an identifiable resource (work), and explicitly differentiates itself from the acceptance sibling by saying it must be called before gateway_work_accept. An agent can tell this completion/evidence-recording step apart from claim, accept, and other work tools.

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 gives explicit sequencing guidance: 'Call this before gateway_work_accept' and explains the consequence of not doing so — 'Acceptance is rejected until successful completion has recorded verification evidence.' This tells the agent exactly when to use this tool versus the acceptance tool.

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