Inspect managed application logs

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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds critical context beyond them: the tool is a POST that queues an inspection despite its 'get_' name, it requires an API key permitting write operations, and requires the applications:read scope. This is exactly the gotcha an agent would otherwise miss from the read-flavored name.

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 the core action, then the pending-follow-up, the service scoping, and the auth caveat. Four dense sentences with little waste, though the auth/permission sentences could be tightened slightly.

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?

With no output schema, the description carries the return-value burden and does describe the return as 'recent, size-bounded container logs,' plus the async inspection.id/polling flow. Response shape details (fields of the inspection result) remain unspecified, but the operational flow is complete.

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 adds meaning for `service` (one exact Compose service; omit to inspect all services) and signals the size-bounding behavior behind `max_bytes`/`tail_lines`, though it adds no detail for orderNo or installation_id beyond the schema.

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+resource: 'Run an on-demand logs inspection of one owned managed application and return recent, size-bounded container logs.' It scopes the operation (single owned application, size-bounded logs) and implicitly distinguishes itself from the sibling get_application_inspection, which it references for the pending follow-up path.

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?

Explicitly tells the agent what to do next when the operation is pending ('retain inspection.id and call get_application_inspection with kind=logs') and names the alternative tool by name. It also states when to supply the `service` parameter vs omit it, and gives the auth precondition (write-permitting key required, read-only key rejected).

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