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

Beyond readOnlyHint it discloses the scan-capped pagination contract (a short page with next_cursor means a row bound was hit, not the end of matches) and the retirement semantics: data_disposal values, what kept_data names, that it reflects a point-in-time Ankra observation, and how to report such a service. This is material context an agent would otherwise get wrong.

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?

Front-loaded with purpose and return shape, then filtering, then the two caveats that matter. It is dense and long for a list tool, with some reporting guidance that verges on instruction rather than definition, but no sentence is filler.

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?

There is no output schema, and the description compensates by enumerating the returned fields including nested consumer and kept_data contents, plus the caveat that kept_data is historical. That is enough for correct invocation and correct reporting.

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%, so baseline is 3; the description still adds meaning by explaining that application_id matches via a reviewed plan naming one of the application's environments as a consumer, and by framing state as the lifecycle in one word. The after/limit semantics are only lightly echoed.

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 and resource ('List the organisation's managed services') and then enumerates exactly what each instance carries: name, package, cluster, deployment state, readiness/health, consumers, latest retirement, lifecycle state. An agent can tell this apart from get_service_instance or list_service_consumers without opening a schema.

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?

Gives concrete selection rules for each filter ('by application_id for the services one application uses, by cluster_id for those running on a cluster, or by state') and explains when to follow next_cursor. It does not explicitly contrast against sibling readers like get_services or get_service_instance, so it stops short of full alternative routing.

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