Get App Tracing

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds genuinely new behavioral context, notably the fixed 7-day span window and the fact that `manual` mode requires the app to supply its own SDK or agent. It discloses what the agent injects at startup, which is non-obvious. It stops short of describing response shape or whether results are cached/live.

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?

One dense but front-loaded sentence leads with the primary return value, followed by a short clarifying sentence on `manual` mode. Every clause carries information, though the long comma-separated list is harder to parse than a short bulleted enumeration would be. No filler wording.

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 does useful work describing the returned fields, so an agent knows what to expect. However, for a four-parameter tool with 0% schema coverage and only a readOnly annotation, omitting all parameter meaning and any notes on access scope leaves the definition incomplete. Adequate, not 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 description coverage is 0% for four parameters, so the description carries the full burden and it says nothing about workspaceSlug, appSlug, env, or region. The `env` enum (production/preview/development) and what `region` scopes are left entirely undocumented. Only the resource-level notion of 'the app's' hints at appSlug, leaving a significant 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 uses a clear verb ('Returns') and enumerates exactly what is returned: monitoring mode, OpenTelemetry variables per compose service, the Cloady agent injected in `auto` mode, and which services have emitted spans. That level of specificity distinguishes it from generic read tools. It never explicitly contrasts with the sibling updateAppTracing, so an agent must infer that this is the read-only counterpart.

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?

Usage is only implied by the read-only nature and the `auto`/`manual` mode distinction, which does convey when this data matters (diagnosing why spans are missing). There is no explicit statement of when to call this versus updateAppTracing, or of prerequisites such as needing workspace/app-level access. An agent can guess the context but is given no routing instruction.

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