list_engine_states

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

With no annotations, the description carries the full burden of behavioral disclosure and delivers: explicit 'Read-only', the 'persisted' nature of the state, and the non-obvious scoping behavior ('scope comes from the session and the project'). This gives an agent confidence about safety and side-effect profile beyond the bare operation.

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?

Three tight sentences, front-loaded with the core purpose, followed by payload/scoping, then filtering and the read-only caveat — every sentence adds information and nothing is redundant fluff. The field enumeration is slightly redundant given an output schema exists, but it is brief and aids tool selection.

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 output schema covers return values, so the description needn't detail them, and it adequately discloses read-only safety in the absence of annotations. The remaining gap is query behavior: limit semantics, pagination/truncation behavior, and how empty default filter values behave are not addressed, which matters for an agent planning a call.

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, and it partially does: engine is clarified with a concrete example ('company_operating_system'), status is explained as a filter, and project_id is contextualized by the session+project scoping note. However, the limit parameter is left entirely unexplained, including its role in capping results.

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 ('List') with a precise resource ('persisted company-engine states of one project') and the output format ('as JSON records'). The field enumeration (engine, entity ref, status, version, plan digest, state digest, sealed state document) makes the returned payload unambiguous and distinguishes this from near-siblings like list_engine_approvals.

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 conveys how to use the tool — filtering by engine and status, with scope derived from the session and project — which is clear operational context. However, it never names alternatives or exclusion conditions, so among hundreds of siblings an agent must infer when this specific list tool is appropriate versus list_engine_approvals or get_engine_inventory.

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