Get managed application state

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral content: it discloses that container samples expose only Compose service and ordinal, and that Docker identities and internal generation digests are withheld, plus that history is bounded and excludes 'internal generation digests'. This is useful redaction/limit context not derivable from the 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?

A single front-loaded sentence led by the verb and resource, with the redaction caveat and the permission requirement following. It is dense but every clause contributes (returned facets, redaction limits, auth). No filler sentences.

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, so the description correctly compensates by enumerating what comes back (health, drift, endpoints, components, bounded resource history, latest action) and stating the required scope. Combined with annotations that carry the safety profile, an agent has enough to call it correctly; only the sibling-routing question remains unanswered.

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?

Both parameters are fully documented in the schema (100% coverage) including the orderNo pattern and installation_id UUID format, so the schema carries the load. The description adds only the implicit ownership scoping ('one owned managed application') and no new per-parameter meaning. 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 specific verb (get) plus a resource (managed application) and enumerates the returned facets - state, health, drift, endpoints, components, resource history, latest action - for 'one owned managed application'. This is far more than a restatement of the name. It stops short of 5 because the sibling set contains near-overlapping reads (get_application_health, get_application_inspection, get_application_events) and none are named or contrasted.

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?

No statement of when to call this versus its many siblings, and no exclusions. The phrase 'one owned managed application' and the 'Requires applications:read' line imply a read-only inspection context, but an agent still has to guess whether this or get_application_health is the right entry point for a health check.

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